Update app.py

app.py

@@ -6,10 +6,68 @@ import matplotlib.pyplot as plt
 import requests
 import json
  
+from urllib.request import urlopen, Request
+from bs4 import BeautifulSoup
+import pandas as pd
+ 
+import nltk
+nltk.downloader.download("vader_lexicon")
+from nltk.sentiment.vader import SentimentIntensityAnalyzer
+
+
+
+
 url_stocks = "https://financialmodelingprep.com/api/v3/stock/list?apikey="
 url_sentiment = "https://yaakovy-fin-proj-docker.hf.space/ticker/"
 url_timeGpt =  "https://ofirmatzlawi-fin-proj-docker-1.hf.space/ticker/"
+finviz_url = "https://finviz.com/quote.ashx?t="
+ 
+
+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)
+    if response.status != 200:   # Check the response status code
+        raise Exception("Failed to fetch news table")
+    html = BeautifulSoup(response)   # Read the contents of the file into 'html'
+    news_table = html.find(id="news-table")   # Find 'news-table' in the Soup and load it into 'news_table'
+    return news_table
+
 
+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           
+            text = x.a.get_text() # get text from a only          
+            date_scrape = x.td.text.split()  # splite text in the td tag into a list
+            if len(date_scrape) == 1: # if the length of 'date_scrape' is 1, load 'time' as the only element
+                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]
+            parsed_news.append([date, time, text])         # Append ticker, date, time and headline as a list to the 'parsed_news' list
+        except:
+            pass
+        columns = ["date", "time", "headline"]   
+        parsed_news_df = pd.DataFrame(parsed_news, columns=columns) # Convert the parsed_news list into a DataFrame called 'parsed_and_scored_news'  
+    return parsed_news_df
+
+def score_news(parsed_news_df):
+    vader = SentimentIntensityAnalyzer()  # Instantiate the sentiment intensity analyzer
+    scores = parsed_news_df["headline"].apply(vader.polarity_scores).tolist()  # Iterate through the headlines and get the polarity scores using vader
+    scores_df = pd.DataFrame(scores)    # Convert the 'scores' list of dicts into a DataFrame
+    parsed_and_scored_news = parsed_news_df.join(scores_df, rsuffix="_right")  # Join the DataFrames of the news and the list of dicts
+    parsed_and_scored_news = parsed_and_scored_news.rename(columns={"compound": "sentiment"})
+    return parsed_and_scored_news
 
 def get_max_sentiment(row):
     if row["sentiment_score"] > 0.05:  # Threshold for positive sentiment
@@ -18,18 +76,7 @@ def get_max_sentiment(row):
         return "negative"
     else:
         return "neutral"
-
-
-
-
-    
-    #max_value = max(row['neg'], row['neu'], row['pos'])
-    #if max_value == row['neg']:
-    #    return 'neg'
-    #elif max_value == row['neu']:
-    #    return 'neu'
-    #else:
-    #    return 'pos'
+ 
 
 
 def get_sentiment_data(stock_info):