app.py

import streamlit as st
from urllib.request import urlopen, Request
from bs4 import BeautifulSoup
import pandas as pd
import plotly.express as px
from dateutil import parser
import nltk
nltk.downloader.download('vader_lexicon')
from nltk.sentiment.vader import SentimentIntensityAnalyzer
import datetime
import requests

st.set_page_config(page_title="Stock News Sentiment Analyzer", layout="wide")

def verify_link(url):
    try:
        response = requests.head(url, timeout=5)
        return response.status_code == 200
    except requests.RequestException:
        return False

def get_news(ticker):
    finviz_url = 'https://finviz.com/quote.ashx?t='
    url = finviz_url + ticker
    req = Request(url=url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:20.0) Gecko/20100101 Firefox/20.0'}) 
    response = urlopen(req)    
    html = BeautifulSoup(response, 'html.parser')
    news_table = html.find(id='news-table')
    return news_table

def parse_news(news_table):
    parsed_news = []
    
    for x in news_table.findAll('tr'):
        try:
            text = x.a.get_text()
            link = x.a['href']
            date_scrape = x.td.text.strip().split()
            
            if len(date_scrape) == 1:
                date = datetime.datetime.today().strftime('%Y-%m-%d')
                time = date_scrape[0]
            else:
                date = date_scrape[0]
                time = date_scrape[1]

            datetime_str = f"{date} {time}"
            datetime_parsed = parser.parse(datetime_str)

            is_valid = verify_link(link)
            
            parsed_news.append([datetime_parsed, text, link, is_valid])
            
        except Exception as e:
            print("Error parsing news:", e)
            continue
    
    columns = ['datetime', 'headline', 'link', 'is_valid']
    parsed_news_df = pd.DataFrame(parsed_news, columns=columns)
    
    return parsed_news_df

def score_news(parsed_news_df):
    vader = SentimentIntensityAnalyzer()
    
    scores = parsed_news_df['headline'].apply(vader.polarity_scores).tolist()
    scores_df = pd.DataFrame(scores)
    parsed_and_scored_news = parsed_news_df.join(scores_df, rsuffix='_right')        
    parsed_and_scored_news = parsed_and_scored_news.set_index('datetime')    
    parsed_and_scored_news = parsed_and_scored_news.rename(columns={"compound": "sentiment_score"})

    return parsed_and_scored_news

def plot_hourly_sentiment(parsed_and_scored_news, ticker):
    numeric_cols = parsed_and_scored_news.select_dtypes(include=['float64', 'int64'])
    mean_scores = numeric_cols.resample('h').mean()
    fig = px.bar(mean_scores, x=mean_scores.index, y='sentiment_score', title=f'{ticker} Hourly Sentiment Scores')
    return fig

def plot_daily_sentiment(parsed_and_scored_news, ticker):
    numeric_cols = parsed_and_scored_news.select_dtypes(include=['float64', 'int64'])
    mean_scores = numeric_cols.resample('D').mean()
    fig = px.bar(mean_scores, x=mean_scores.index, y='sentiment_score', title=f'{ticker} Daily Sentiment Scores')
    return fig

st.header("Stock News Sentiment Analyzer")

ticker = st.text_input('Enter Stock Ticker', '').upper()

try:
    st.subheader(f"Hourly and Daily Sentiment of {ticker} Stock")
    news_table = get_news(ticker)
    parsed_news_df = parse_news(news_table)
    parsed_and_scored_news = score_news(parsed_news_df)
    fig_hourly = plot_hourly_sentiment(parsed_and_scored_news, ticker)
    fig_daily = plot_daily_sentiment(parsed_and_scored_news, ticker) 
     
    st.plotly_chart(fig_hourly)
    st.plotly_chart(fig_daily)

    description = f"""
        The above chart averages the sentiment scores of {ticker} stock hourly and daily.
        The table below gives each of the most recent headlines of the stock and the negative, neutral, positive and an aggregated sentiment score.
        The news headlines are obtained from the FinViz website.
        Sentiments are given by the nltk.sentiment.vader Python library.
        Links have been verified for validity.
        """
        
    st.write(description)     
    
    parsed_and_scored_news['link'] = parsed_and_scored_news.apply(
        lambda row: f'<a href="{row["link"]}" target="_blank">{"Valid" if row["is_valid"] else "Invalid"} Link</a>', 
        axis=1
    )
    
    st.write(parsed_and_scored_news.drop(columns=['is_valid']).to_html(escape=False), unsafe_allow_html=True)
    
except Exception as e:
    print(str(e))
    st.write("Enter a correct stock ticker, e.g. 'AAPL' above and hit Enter.")    

hide_streamlit_style = """
<style>
#MainMenu {visibility: hidden;}
footer {visibility: hidden;}
</style>
"""
st.markdown(hide_streamlit_style, unsafe_allow_html=True)