app.py

import streamlit as st
from urllib.request import urlopen, Request
from bs4 import BeautifulSoup
import pandas as pd
import json # for graph plotting in website
# NLTK VADER for sentiment analysis
import nltk
nltk.downloader.download('vader_lexicon')
from nltk.sentiment.vader import SentimentIntensityAnalyzer

import subprocess
import os

import datetime

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


def get_news(ticker):
    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)
    # Read the contents of the file into 'html'
    html = BeautifulSoup(response)
    # Find 'news-table' in the Soup and load it into 'news_table'
    news_table = html.find(id='news-table')
    return news_table

# parse news into dataframe
def parse_news(news_table):
    parsed_news = []
    today_string = datetime.datetime.today().strftime('%Y-%m-%d')

    for x in news_table.findAll('tr'):
        try:
            # read the text from each tr tag into text
            # get text from a only
            text = x.a.get_text()
            # splite text in the td tag into a list
            date_scrape = x.td.text.split()
            # if the length of 'date_scrape' is 1, load 'time' as the only element

            if len(date_scrape) == 1:
                time = date_scrape[0]

            # else load 'date' as the 1st element and 'time' as the second
            else:
                date = date_scrape[0]
                time = date_scrape[1]

            # Append ticker, date, time and headline as a list to the 'parsed_news' list
            parsed_news.append([date, time, text])
        except:
            pass

        # Set column names
        columns = ['date', 'time', 'headline']
        # Convert the parsed_news list into a DataFrame called 'parsed_and_scored_news'
        parsed_news_df = pd.DataFrame(parsed_news, columns=columns)
        # Create a pandas datetime object from the strings in 'date' and 'time' column
        parsed_news_df['date'] = parsed_news_df['date'].replace("Today", today_string)
        parsed_news_df['datetime'] = pd.to_datetime(parsed_news_df['date'] + ' ' + parsed_news_df['time'])

    return parsed_news_df



def score_news(parsed_news_df):
    # Instantiate the sentiment intensity analyzer
    vader = SentimentIntensityAnalyzer()

    # Iterate through the headlines and get the polarity scores using vader
    scores = parsed_news_df['headline'].apply(vader.polarity_scores).tolist()

    # Convert the 'scores' list of dicts into a DataFrame
    scores_df = pd.DataFrame(scores)

    # Join the DataFrames of the news and the list of dicts
    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.drop(['date', 'time'], 1)
    parsed_and_scored_news = parsed_and_scored_news.rename(columns={"compound": "sentiment_score"})

    return parsed_and_scored_news

# for extracting data from finviz
finviz_url = 'https://finviz.com/quote.ashx?t='


st.header("Data Sience Project: Stock News Sentiment Analyzer")

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

df = pd.DataFrame({'datetime': datetime.datetime.now(), 'ticker': ticker}, index = [0])


try:
	st.subheader("Hourly and Daily Sentiment of {} Stock".format(ticker))
	news_table = get_news(ticker)
	parsed_news_df = parse_news(news_table)
	print(parsed_news_df)
	parsed_and_scored_news = score_news(parsed_news_df)
	st.table(parsed_and_scored_news)

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)