Update app.py

app.py

@@ -0,0 +1,163 @@
+import streamlit as st
+import requests
+from bs4 import BeautifulSoup
+from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
+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, .stTextArea textarea {
+            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 -----------
+sentiment_model_id = "LinkLinkWu/Boss_Stock_News_Analysis"
+sentiment_tokenizer = AutoTokenizer.from_pretrained(sentiment_model_id)
+sentiment_model = AutoModelForSequenceClassification.from_pretrained(sentiment_model_id)
+sentiment_pipeline = pipeline("sentiment-analysis", model=sentiment_model, tokenizer=sentiment_tokenizer)
+
+ner_tokenizer = AutoTokenizer.from_pretrained("dslim/bert-base-NER")
+ner_model = AutoModelForTokenClassification.from_pretrained("dslim/bert-base-NER")
+ner_pipeline = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer, grouped_entities=True)
+
+# ----------- Functions -----------
+def fetch_news(ticker):
+    try:
+        url = f"https://finviz.com/quote.ashx?t={ticker}"
+        headers = {
+            'User-Agent': 'Mozilla/5.0',
+            'Accept': 'text/html',
+            '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]:
+            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"
+
+def extract_org_entities(text):
+    try:
+        entities = ner_pipeline(text)
+        org_entities = []
+        for ent in entities:
+            if ent["entity_group"] == "ORG":
+                clean_word = ent["word"].replace("##", "").strip()
+                if clean_word.upper() not in org_entities:
+                    org_entities.append(clean_word.upper())
+                if len(org_entities) >= 5:
+                    break
+        return org_entities
+    except Exception as e:
+        st.error(f"NER entity extraction failed: {e}")
+        return []
+
+# ----------- UI -----------
+st.title("\U0001F4CA Stock News Sentiment Analysis")
+st.markdown("""
+This tool analyzes the sentiment of news articles related to companies you mention in text.
+\U0001F4A1 *Try input like:* `I want to check Apple, Tesla, and Microsoft.`
+**Note:** If news fetching fails, it may be due to changes in the Finviz website or access restrictions.
+""")
+
+free_text = st.text_area("Enter text mentioning companies:", height=100)
+tickers = extract_org_entities(free_text)
+
+if tickers:
+    cleaned_input = ", ".join(tickers)
+    st.markdown(f"\U0001F50E **Identified Tickers:** `{cleaned_input}`")
+else:
+    tickers = []
+
+if st.button("Get News and Sentiment"):
+    if not tickers:
+        st.warning("Please mention at least one recognizable company.")
+    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:
+                sentiments = []
+                for news in news_list:
+                    sentiment = analyze_sentiment(news['title'])
+                    sentiments.append(sentiment)
+
+                positive_count = sentiments.count("Positive")
+                negative_count = sentiments.count("Negative")
+                total = len(sentiments)
+                positive_ratio = positive_count / total if total else 0
+                negative_ratio = negative_count / total if total else 0
+
+                if positive_ratio >= 0.4:
+                    overall_sentiment = "Positive"
+                elif negative_ratio >= 0.6:
+                    overall_sentiment = "Negative"
+                else:
+                    overall_sentiment = "Neutral"
+
+                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}**")
+
+                if overall_sentiment != "Undecided":
+                    st.write(f"**Overall Sentiment for {ticker}: {overall_sentiment}**")
+                else:
+                    st.write("**No clear sentiment (does not meet threshold conditions).**")
+            else:
+                st.write(f"No news available for {ticker}.")
+
+            progress_bar.progress((idx + 1) / total_stocks)
+            time.sleep(0.1)