app.py

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

app = Flask(__name__)

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

@app.route('/')
def loading():
    return render_template("loading.html")

@app.route('/load_feeds', methods=['GET'])
def load_feeds():
    logger.info("Starting to fetch and process RSS feeds")
    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")
    return Response("Feeds loaded", status=200)

@app.route('/index', methods=['GET'])
def index():
    stored_docs = vector_db.similarity_search("news", k=1000)  # Increased k to ensure all unique articles
    # Use a set to ensure unique articles by title and link
    unique_articles = {}
    for doc in stored_docs:
        key = f"{doc.metadata['title']}|{doc.metadata['link']}"
        if key not in unique_articles:
            unique_articles[key] = {
                "title": doc.metadata["title"],
                "link": doc.metadata["link"],
                "description": doc.metadata["original_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")

    if request.method == 'POST' and 'search' in request.form:
        query = request.form.get('search')
        if query:
            logger.info(f"Processing search query: {query}")
            results = vector_db.similarity_search(query, k=10)
            unique_search_articles = {}
            for doc in results:
                key = f"{doc.metadata['title']}|{doc.metadata['link']}"
                if key not in unique_search_articles:
                    unique_search_articles[key] = {
                        "title": doc.metadata["title"],
                        "link": doc.metadata["link"],
                        "description": doc.metadata["original_description"],
                        "category": doc.metadata["category"],
                        "published": doc.metadata["published"],
                        "image": doc.metadata.get("image", "svg"),
                    }
            enriched_articles = list(unique_search_articles.values())
            logger.info(f"Search returned {len(enriched_articles)} unique results")

    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)

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