app.py

import os
import subprocess
from flask import Flask, render_template, request, Response, jsonify
from rss_processor import fetch_rss_feeds, process_and_store_articles, vector_db
import logging
import time
import hashlib

app = Flask(__name__)

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

def load_feeds_in_background():
    logger.info("Starting to fetch and process RSS feeds in background")
    start_time = time.time()
    articles = fetch_rss_feeds()
    logger.info(f"Fetched {len(articles)} articles")
    process_and_store_articles(articles)
    logger.info("Articles processed and stored")
    end_time = time.time()
    logger.info(f"RSS feed loading took {end_time - start_time:.2f} seconds")

@app.route('/')
def index():
    # Show existing articles immediately
    stored_docs = vector_db.similarity_search("news", k=1000)  # Show all available articles
    # Use a set to ensure unique articles by title, link, and description hash
    unique_articles = {}
    for doc in stored_docs:
        title = doc.metadata["title"]
        link = doc.metadata["link"]
        description = doc.metadata["original_description"]
        desc_hash = hashlib.md5(description.encode()).hexdigest()[:10]
        key = f"{title}|{link}|{desc_hash}"
        if key not in unique_articles:
            unique_articles[key] = {
                "title": title,
                "link": link,
                "description": description,
                "category": doc.metadata["category"],
                "published": doc.metadata["published"],
                "image": doc.metadata.get("image", "svg"),
            }
    enriched_articles = list(unique_articles.values())
    logger.info(f"Enriched {len(enriched_articles)} unique articles for display")

    # Start loading new feeds in the background
    subprocess.Popen(["python", "rss_processor.py", "load_feeds"])

    categorized_articles = {}
    for article in enriched_articles:
        cat = article["category"]
        if cat not in categorized_articles:
            categorized_articles[cat] = []
        categorized_articles[cat].append(article)

    return render_template("index.html", categorized_articles=categorized_articles, loading_new_feeds=True)

@app.route('/check_feeds', methods=['GET'])
def check_feeds():
    try:
        # Check if vector DB has new documents (simplified check)
        docs = vector_db.similarity_search("news", k=1)
        if docs:
            logger.info("Feeds loaded successfully in vector DB")
            return jsonify({"status": "loaded"})
        return jsonify({"status": "loading"}), 202
    except Exception as e:
        logger.error(f"Error checking feeds: {e}")
        return jsonify({"status": "error", "message": str(e)}), 500

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)