import os
import feedparser
from langchain.vectorstores import Chroma
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.docstore.document import Document
import logging

# Setup logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Constants
LOCAL_DB_DIR = "chroma_db"
RSS_FEEDS = [
    "https://www.sciencedaily.com/rss/top/science.xml",
    "https://www.horoscope.com/us/horoscopes/general/rss/horoscope-rss.aspx",
    "http://rss.cnn.com/rss/cnn_allpolitics.rss",
    "https://phys.org/rss-feed/physics-news/",
    "https://www.spaceweatherlive.com/en/news/rss",
    "https://weather.com/feeds/rss",
    "https://www.wired.com/feed/rss",
    "https://www.nasa.gov/rss/dyn/breaking_news.rss",
    "https://www.nationalgeographic.com/feed/",
    "https://www.nature.com/nature.rss",
    "https://www.scientificamerican.com/rss/",
    "https://www.newscientist.com/feed/home/",
    "https://www.livescience.com/feeds/all",
    "https://astrostyle.com/feed/",
    "https://www.vogue.com/feed/rss",
    "https://feeds.bbci.co.uk/news/politics/rss.xml",
    "https://www.reuters.com/arc/outboundfeeds/newsletter-politics/?outputType=xml",
    "https://www.politico.com/rss/politics.xml",
    "https://thehill.com/feed/",
    "https://www.aps.org/publications/apsnews/updates/rss.cfm",
    "https://www.quantamagazine.org/feed/",
    "https://www.sciencedaily.com/rss/matter_energy/physics.xml",
    "https://physicsworld.com/feed/",
    "https://www.swpc.noaa.gov/rss.xml",
    "https://feeds.bbci.co.uk/weather/feeds/rss/5day/world/",
    "https://www.weather.gov/rss",
    "https://www.foxweather.com/rss",
    "https://techcrunch.com/feed/",
    "https://arstechnica.com/feed/",
    "https://gizmodo.com/rss",
    "https://www.theverge.com/rss/index.xml",
    "https://www.space.com/feeds/all",
    "https://www.universetoday.com/feed/",
    "https://skyandtelescope.org/feed/",
    "https://www.esa.int/rss",
    "https://www.smithsonianmag.com/rss/",
    "https://www.popsci.com/rss.xml",
    "https://www.discovermagazine.com/rss",
    "https://www.atlasobscura.com/feeds/latest"
]

# Initialize embedding model and vector DB
embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
vector_db = Chroma(persist_directory=LOCAL_DB_DIR, embedding_function=embedding_model)

def fetch_rss_feeds():
    articles = []
    seen_keys = set()
    for feed_url in RSS_FEEDS:
        try:
            logger.info(f"Fetching {feed_url}")
            feed = feedparser.parse(feed_url)
            if feed.bozo:
                logger.warning(f"Parse error for {feed_url}: {feed.bozo_exception}")
                continue
            for entry in feed.entries:
                title = entry.get("title", "No Title")
                link = entry.get("link", "")
                description = entry.get("summary", entry.get("description", "No Description"))
                key = f"{title}|{link}"
                if key not in seen_keys:
                    seen_keys.add(key)
                    image = (entry.get("media_content", [{}])[0].get("url") or
                             entry.get("media_thumbnail", [{}])[0].get("url") or "svg")
                    articles.append({
                        "title": title,
                        "link": link,
                        "description": description,
                        "published": entry.get("published", "Unknown Date"),
                        "category": categorize_feed(feed_url),
                        "image": image,
                    })
        except Exception as e:
            logger.error(f"Error fetching {feed_url}: {e}")
    logger.info(f"Total articles fetched: {len(articles)}")
    return articles

def categorize_feed(url):
    if "sciencedaily" in url:
        return "Science"
    elif "nasa" in url:
        return "Space"
    elif "wired" in url:
        return "Tech"
    return "Uncategorized"

def process_and_store_articles(articles):
    documents = []
    for article in articles:
        try:
            metadata = {
                "title": article["title"],
                "link": article["link"],
                "original_description": article["description"],
                "published": article["published"],
                "category": article["category"],
                "image": article["image"],
            }
            doc = Document(page_content=article["description"], metadata=metadata)
            documents.append(doc)
        except Exception as e:
            logger.error(f"Error processing article {article['title']}: {e}")
    
    if documents:
        try:
            vector_db.add_documents(documents)
            logger.info(f"Stored {len(documents)} articles in DB")
        except Exception as e:
            logger.error(f"Error storing articles: {e}")

if __name__ == "__main__":
    articles = fetch_rss_feeds()
    process_and_store_articles(articles)