Delete app.py

app.py

@@ -1,188 +0,0 @@
-
-import time
-import sqlite3
-import feedparser
-from newspaper import Article, Config
-import nltk
-from nltk.sentiment.vader import SentimentIntensityAnalyzer
-import gradio as gr
-
-# Download the VADER lexicon if not already downloaded.
-nltk.download('vader_lexicon')
-
-#############################################
-# Database Setup (SQLite)
-#############################################
-
-# Connect to (or create) the SQLite database.
-# Use check_same_thread=False for use within Gradio's threaded server.
-conn = sqlite3.connect('crypto_news.db', check_same_thread=False)
-cursor = conn.cursor()
-
-# Create a table to store articles. The URL field is UNIQUE to avoid duplicates.
-cursor.execute('''
-CREATE TABLE IF NOT EXISTS articles (
-    id INTEGER PRIMARY KEY AUTOINCREMENT,
-    source TEXT,
-    title TEXT,
-    url TEXT UNIQUE,
-    content TEXT,
-    sentiment REAL,
-    published TEXT,
-    fetched_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
-)
-''')
-conn.commit()
-
-#############################################
-# Sentiment Analysis Setup
-#############################################
-
-# Initialize NLTK's VADER sentiment analyzer.
-sid = SentimentIntensityAnalyzer()
-
-def analyze_sentiment(text):
-    """Return the compound sentiment score for the given text."""
-    scores = sid.polarity_scores(text)
-    return scores['compound']
-
-def store_article(source, title, url, content, sentiment, published):
-    """Insert an article into the database (ignoring duplicates)."""
-    try:
-        cursor.execute('''
-        INSERT INTO articles (source, title, url, content, sentiment, published)
-        VALUES (?, ?, ?, ?, ?, ?)
-        ''', (source, title, url, content, sentiment, published))
-        conn.commit()
-        print(f"Stored article: {title}")
-    except sqlite3.IntegrityError:
-        print(f"Article already exists in DB: {title}")
-
-#############################################
-# Article Fetching with Newspaper3k
-#############################################
-
-def fetch_article(url):
-    """
-    Download and parse a news article using Newspaper3k.
-    Returns the parsed article object, or None on error.
-    """
-    try:
-        # Set a browser-like user agent to avoid 403 errors.
-        user_agent = (
-            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
-            'AppleWebKit/537.36 (KHTML, like Gecko) '
-            'Chrome/90.0.4430.93 Safari/537.36'
-        )
-        config = Config()
-        config.browser_user_agent = user_agent
-
-        article = Article(url, config=config)
-        article.download()
-        article.parse()
-        return article
-    except Exception as e:
-        print(f"Error fetching article from {url}: {e}")
-        return None
-
-#############################################
-# RSS Feed Processing
-#############################################
-
-def fetch_feed(feed_url, source_name):
-    """
-    Parse an RSS feed and process each entry: download the full article,
-    analyze its sentiment, and store it in the database.
-    """
-    feed = feedparser.parse(feed_url)
-    if feed.bozo:
-        print(f"Error parsing feed from {source_name}: {feed.bozo_exception}")
-        return
-
-    for entry in feed.entries:
-        title = entry.get('title', 'No Title')
-        url = entry.get('link', None)
-        published = entry.get('published', '')
-        if not url:
-            continue
-
-        article = fetch_article(url)
-        if article and article.text:
-            content = article.text
-            sentiment = analyze_sentiment(content)
-            store_article(source_name, title, url, content, sentiment, published)
-        else:
-            print(f"Skipping article (no content): {title}")
-
-def update_feeds():
-    """
-    Loop over a list of free crypto news RSS feeds and fetch articles.
-    """
-    feeds = [
-        {'url': 'https://www.coindesk.com/arc/outboundfeeds/rss/?outputType=xml', 'source': 'CoinDesk'},
-        {'url': 'https://cointelegraph.com/rss', 'source': 'Cointelegraph'},
-        {'url': 'https://cryptoslate.com/feed/', 'source': 'CryptoSlate'},
-        {'url': 'https://www.newsbtc.com/feed/', 'source': 'NewsBTC'},
-        {'url': 'https://decrypt.co/feed', 'source': 'Decrypt'},
-    ]
-    for feed in feeds:
-        print(f"Fetching feed from {feed['source']}...")
-        fetch_feed(feed['url'], feed['source'])
-
-#############################################
-# Retrieve and Format Latest News for Display
-#############################################
-
-def get_latest_news():
-    """
-    Retrieve the latest 10 articles from the database and format them into an HTML string.
-    """
-    cursor.execute("""
-        SELECT source, title, url, sentiment, published 
-        FROM articles 
-        ORDER BY fetched_at DESC 
-        LIMIT 10
-    """)
-    articles = cursor.fetchall()
-    
-    html_str = "<h2>Latest Crypto News</h2>"
-    if not articles:
-        html_str += "<p>No articles found. Try fetching news first.</p>"
-    else:
-        for article in articles:
-            source, title, url, sentiment, published = article
-            html_str += "<div style='margin-bottom:20px; border-bottom:1px solid #ccc; padding-bottom:10px;'>"
-            html_str += f"<h3>{title}</h3>"
-            html_str += f"<p><strong>Source:</strong> {source} | "
-            html_str += f"<strong>Published:</strong> {published} | "
-            html_str += f"<strong>Sentiment:</strong> {sentiment}</p>"
-            html_str += f"<p><a href='{url}' target='_blank'>Read full article</a></p>"
-            html_str += "</div>"
-    return html_str
-
-#############################################
-# Gradio Callback Function
-#############################################
-
-def fetch_and_display_news():
-    """
-    Update the database by fetching articles from all RSS feeds,
-    then return an HTML-formatted list of the latest articles.
-    """
-    update_feeds()
-    return get_latest_news()
-
-#############################################
-# Gradio Interface
-#############################################
-
-iface = gr.Interface(
-    fn=fetch_and_display_news,
-    inputs=[],   # No inputs: clicking the button triggers fetching.
-    outputs="html",
-    title="Crypto News Dashboard",
-    description="Click the button to fetch the latest cryptocurrency news from free news sources."
-)
-
-if __name__ == "__main__":
-    iface.launch()