library-desk/src/apis/bbc.py

"""
BBC News RSS client.

Free RSS feeds from BBC News.
https://www.bbc.com/news/10628494 (RSS feed directory)

No API key required.
"""

import httpx
import feedparser
import logging
from datetime import datetime
from email.utils import parsedate_to_datetime
from typing import Optional

from .base import NewsProvider, NewsItem, NewsFeed

logger = logging.getLogger(__name__)


class BBCProvider(NewsProvider):
    """BBC News RSS feed implementation."""

    # Available BBC RSS feeds
    FEEDS: dict[str, str] = {
        # News
        "top": "https://feeds.bbci.co.uk/news/rss.xml",
        "world": "https://feeds.bbci.co.uk/news/world/rss.xml",
        "uk": "https://feeds.bbci.co.uk/news/uk/rss.xml",
        "business": "https://feeds.bbci.co.uk/news/business/rss.xml",
        "politics": "https://feeds.bbci.co.uk/news/politics/rss.xml",
        "health": "https://feeds.bbci.co.uk/news/health/rss.xml",
        "education": "https://feeds.bbci.co.uk/news/education/rss.xml",
        "science": "https://feeds.bbci.co.uk/news/science_and_environment/rss.xml",
        "tech": "https://feeds.bbci.co.uk/news/technology/rss.xml",
        "entertainment": "https://feeds.bbci.co.uk/news/entertainment_and_arts/rss.xml",
        "asia": "https://feeds.bbci.co.uk/news/world/asia/rss.xml",
        "europe": "https://feeds.bbci.co.uk/news/world/europe/rss.xml",
        "africa": "https://feeds.bbci.co.uk/news/world/africa/rss.xml",
        # Sports
        "sports": "https://feeds.bbci.co.uk/sport/rss.xml",
        "football": "https://feeds.bbci.co.uk/sport/football/rss.xml",
        "cricket": "https://feeds.bbci.co.uk/sport/cricket/rss.xml",
        "tennis": "https://feeds.bbci.co.uk/sport/tennis/rss.xml",
        "rugby": "https://feeds.bbci.co.uk/sport/rugby-union/rss.xml",
        "f1": "https://feeds.bbci.co.uk/sport/motorsport/rss.xml",
        "golf": "https://feeds.bbci.co.uk/sport/golf/rss.xml",
    }

    def __init__(self, timeout: int = 10):
        """
        Initialize BBC RSS client.

        Args:
            timeout: HTTP request timeout in seconds
        """
        self.timeout = timeout
        self._client: Optional[httpx.AsyncClient] = None

    @property
    def client(self) -> httpx.AsyncClient:
        """Lazy-initialize HTTP client."""
        if self._client is None or self._client.is_closed:
            self._client = httpx.AsyncClient(timeout=self.timeout)
        return self._client

    async def close(self):
        """Close HTTP client."""
        if self._client and not self._client.is_closed:
            await self._client.aclose()
            self._client = None

    @property
    def source_name(self) -> str:
        """Provider name."""
        return "bbc"

    @property
    def available_categories(self) -> list[str]:
        """List of available category keys."""
        return list(self.FEEDS.keys())

    async def get_feed(self, category: str, limit: int = 10) -> NewsFeed:
        """
        Get news feed for a category.

        Args:
            category: Feed category (top, world, uk, business, etc.)
            limit: Maximum number of items to return

        Returns:
            NewsFeed with standardized news items

        Raises:
            ValueError: If category is not available
        """
        if category not in self.FEEDS:
            raise ValueError(
                f"Unknown category '{category}'. "
                f"Available: {', '.join(self.available_categories)}"
            )

        feed_url = self.FEEDS[category]

        try:
            response = await self.client.get(feed_url)
            response.raise_for_status()

            # Parse RSS feed
            feed = feedparser.parse(response.text)

            items = []
            for entry in feed.entries[:limit]:
                # Parse publication date
                published = None
                if hasattr(entry, 'published'):
                    try:
                        published = parsedate_to_datetime(entry.published)
                    except (TypeError, ValueError):
                        pass

                # BBC uses media:thumbnail for images
                image_url = None
                if hasattr(entry, 'media_thumbnail') and entry.media_thumbnail:
                    image_url = entry.media_thumbnail[0].get('url')
                elif hasattr(entry, 'media_content') and entry.media_content:
                    image_url = entry.media_content[0].get('url')

                items.append(NewsItem(
                    title=entry.get('title', 'No title'),
                    description=entry.get('summary') or entry.get('description'),
                    url=entry.get('link', ''),
                    published=published,
                    source=self.source_name,
                    category=category,
                    image_url=image_url
                ))

            return NewsFeed(
                source=self.source_name,
                category=category,
                items=items,
                fetched_at=datetime.now()
            )

        except httpx.HTTPError as e:
            logger.error(f"BBC feed request failed for '{category}': {e}")
            raise ValueError(f"Failed to fetch BBC feed: {e}")
        except Exception as e:
            logger.error(f"Failed to parse BBC feed '{category}': {e}")
            raise ValueError(f"Failed to parse BBC feed: {e}")