app.py

import streamlit as st
import requests
from bs4 import BeautifulSoup
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import time

# ----------- Page Layout & Custom Styling -----------
st.set_page_config(page_title="Stock News Sentiment Analysis", layout="centered")

st.markdown("""
    <style>
        .main { background-color: #f9fbfc; }
        .stTextInput>div>div>input {
            font-size: 16px;
            padding: 0.5rem;
        }
        .stButton>button {
            background-color: #4CAF50;
            color: white;
            font-size: 16px;
            padding: 0.5rem 1rem;
            border-radius: 8px;
        }
        .stButton>button:hover {
            background-color: #45a049;
        }
    </style>
""", unsafe_allow_html=True)

# ----------- Model Setup -----------
model_id = "LinkLinkWu/Boss_Stock_News_Analysis"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)
sentiment_pipeline = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

# ----------- Function Definitions -----------
def fetch_news(ticker):
    try:
        url = f"https://finviz.com/quote.ashx?t={ticker}"
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'Accept-Language': 'en-US,en;q=0.5',
            'Referer': 'https://finviz.com/',
            'Connection': 'keep-alive',
        }
        response = requests.get(url, headers=headers)
        if response.status_code != 200:
            st.error(f"Failed to fetch page for {ticker}: Status code {response.status_code}")
            return []
        
        soup = BeautifulSoup(response.text, 'html.parser')
        title = soup.title.text if soup.title else ""
        if ticker not in title:
            st.error(f"Page for {ticker} not found or access denied.")
            return []
        
        news_table = soup.find(id='news-table')
        if news_table is None:
            st.error(f"News table not found for {ticker}. The website structure might have changed.")
            return []
        
        news = []
        for row in news_table.findAll('tr')[:50]:  # Fetch up to 50 articles
            a_tag = row.find('a')
            if a_tag:
                title = a_tag.get_text()
                link = a_tag['href']
                news.append({'title': title, 'link': link})
        return news
    except Exception as e:
        st.error(f"Failed to fetch news for {ticker}: {e}")
        return []

def analyze_sentiment(text):
    try:
        result = sentiment_pipeline(text)[0]
        return "Positive" if result['label'] == 'POSITIVE' else "Negative"
    except Exception as e:
        st.error(f"Sentiment analysis failed: {e}")
        return "Unknown"

# ----------- Streamlit UI -----------
st.title("📊 Stock News Sentiment Analysis")
st.markdown("""
This tool parses stock tickers and analyzes the sentiment of related news articles.

💡 *Example input:* `META, NVDA, AAPL, NTES, NCTY`

**Note:** If news fetching fails, it might be due to changes in the Finviz website structure or access restrictions. Please verify the website manually or try again later.
""")

# Input field for stock tickers
tickers_input = st.text_input("Enter stock tickers separated by commas:", "META, NVDA, AAPL, NTES, NCTY")

# Parse and display cleaned tickers in real-time
if tickers_input:
    tickers = [ticker.strip().upper() for ticker in tickers_input.split(",") if ticker.strip()]
    cleaned_input = ", ".join(tickers)
    st.markdown(f"🔎 **Parsed Tickers:** `{cleaned_input}`")
else:
    tickers = []

# Button to trigger sentiment analysis
if st.button("Get News and Sentiment"):
    if not tickers:
        st.warning("Please enter at least one stock ticker.")
    else:
        progress_bar = st.progress(0)
        total_stocks = len(tickers)
        for idx, ticker in enumerate(tickers):
            st.subheader(f"Analyzing {ticker}...")
            news_list = fetch_news(ticker)
            
            if news_list:
                # Analyze sentiment for all news articles (up to 50)
                sentiments = []
                for news in news_list:
                    sentiment = analyze_sentiment(news['title'])
                    sentiments.append(sentiment)
                
                # Determine overall sentiment based on majority
                positive_count = sentiments.count("Positive")
                negative_count = sentiments.count("Negative")
                overall_sentiment = "Positive" if positive_count > negative_count else "Negative"
                
                # Display top 3 news articles with sentiment
                st.write(f"**Top 3 News Articles for {ticker}**")
                for i, news in enumerate(news_list[:3], 1):
                    sentiment = sentiments[i-1]
                    st.markdown(f"{i}. [{news['title']}]({news['link']}) - **{sentiment}**")
                
                # Display overall sentiment
                st.write(f"**Overall Sentiment for {ticker}: {overall_sentiment}**")
            else:
                st.write(f"No news available for {ticker}.")
            
            # Update progress bar
            progress_bar.progress((idx + 1) / total_stocks)
            time.sleep(0.1)  # Simulate processing time