Update app.py

app.py

@@ -1,75 +1,94 @@
 import gradio as gr
-import selenium
 import requests
 from bs4 import BeautifulSoup
 import pandas as pd
-
-from selenium import webdriver
-from selenium.webdriver.common.keys import Keys
-import pandas as pd
-import time
 from transformers import pipeline
+import plotly.graph_objects as go
+from datetime import datetime, timedelta
 
-# Search Query
-def news_and_analysis(query):
+# Sentiment Analysis Model
+sentiment_model = pipeline(model="finiteautomata/bertweet-base-sentiment-analysis")
 
-# Encode special characters in a text string
-    def encode_special_characters(text):
-        encoded_text = ''
-        special_characters = {'&': '%26', '=': '%3D', '+': '%2B', ' ': '%20'}  # Add more special characters as needed
-        for char in text.lower():
-            encoded_text += special_characters.get(char, char)
-        return encoded_text
+# Function to encode special characters in the search query
+def encode_special_characters(text):
+    encoded_text = ''
+    special_characters = {'&': '%26', '=': '%3D', '+': '%2B', ' ': '%20'}
+    for char in text.lower():
+        encoded_text += special_characters.get(char, char)
+    return encoded_text
 
-    query2 = encode_special_characters(query)
-    url = f"https://news.google.com/search?q={query2}&hl=en-US&gl=in&ceid=US%3Aen&num=3"
-
-    response = requests.get(url, verify = False)
+# Function to fetch news articles
+def fetch_news(query, num_articles=10):
+    encoded_query = encode_special_characters(query)
+    url = f"https://news.google.com/search?q={encoded_query}&hl=en-US&gl=in&ceid=US%3Aen&num={num_articles}"
+    
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+    except requests.RequestException as e:
+        print(f"Error fetching news: {e}")
+        return pd.DataFrame()
+    
     soup = BeautifulSoup(response.text, 'html.parser')
-
     articles = soup.find_all('article')
-    links = [article.find('a')['href'] for article in articles]
-    links = [link.replace("./articles/", "https://news.google.com/articles/") for link in links]
-
-    news_text = [article.get_text(separator='\n') for article in articles]
-    news_text_split = [text.split('\n') for text in news_text]
-
-    news_df = pd.DataFrame({
-        'Title': [text[2] for text in news_text_split],
-        'Source': [text[0] for text in news_text_split],
-        'Time': [text[3] if len(text) > 3 else 'Missing' for text in news_text_split],
-        'Author': [text[4].split('By ')[-1] if len(text) > 4 else 'Missing' for text in news_text_split],
-        'Link': links
-    })
+    
+    news_data = []
+    for article in articles[:num_articles]:
+        link = article.find('a')['href'].replace("./articles/", "https://news.google.com/articles/")
+        text_parts = article.get_text(separator='\n').split('\n')
+        
+        news_data.append({
+            'Title': text_parts[2] if len(text_parts) > 2 else 'Missing',
+            'Source': text_parts[0] if len(text_parts) > 0 else 'Missing',
+            'Time': text_parts[3] if len(text_parts) > 3 else 'Missing',
+            'Author': text_parts[4].split('By ')[-1] if len(text_parts) > 4 else 'Missing',
+            'Link': link
+        })
+    
+    return pd.DataFrame(news_data)
 
-    news_df = news_df.loc[0:5,:]
-    options = webdriver.ChromeOptions()
-    options.add_argument('--headless')
-    options.add_argument('--no-sandbox')
-    options.add_argument('--disable-dev-shm-usage')
-    options.use_chromium = True
-    driver = webdriver.Chrome(options = options)
+# Function to perform sentiment analysis
+def analyze_sentiment(text):
+    result = sentiment_model(text)[0]
+    return result['label'], result['score']
 
-    classification= pipeline(model="finiteautomata/bertweet-base-sentiment-analysis")
+# Main function to process news and perform analysis
+def news_and_analysis(query):
+    # Fetch news
+    news_df = fetch_news(query)
     
-    news_df['Sentiment'] = ''
-    for i in range(0, len(news_df)):
-        # driver.get(news_df.loc[i,'Link'])
-        # time.sleep(10)
-        # headline = driver.find_element('xpath', '//h1').text
-        #news_df.loc[i, 'Headline'] = headline
-        title = news_df.loc[i, 'Title']
-        news_df.loc[i, 'Sentiment'] = str(classification(title))
-        print(news_df)
-
-    return(news_df)
+    if news_df.empty:
+        return "No news articles found.", None
+    
+    # Perform sentiment analysis
+    news_df['Sentiment'], news_df['Sentiment_Score'] = zip(*news_df['Title'].apply(analyze_sentiment))
+    
+    # Create sentiment plot
+    sentiment_fig = go.Figure(data=[go.Bar(
+        x=news_df['Time'],
+        y=news_df['Sentiment_Score'],
+        marker_color=news_df['Sentiment'].map({'positive': 'green', 'neutral': 'gray', 'negative': 'red'})
+    )])
+    sentiment_fig.update_layout(title='News Sentiment Over Time', xaxis_title='Time', yaxis_title='Sentiment Score')
+    
+    return news_df, sentiment_fig
 
+# Gradio interface
 with gr.Blocks() as demo:
-
-  
-    topic= gr.Textbox(label="Topic for which you want Google news and sentiment analysis")
+    gr.Markdown("# Financial News Sentiment Analysis")
+    
+    topic = gr.Textbox(label="Enter a financial topic or company name")
+    
+    analyze_btn = gr.Button(value="Analyze")
+    
+    news_output = gr.DataFrame(label="News and Sentiment Analysis")
+    sentiment_plot = gr.Plot(label="Sentiment Analysis")
     
-    btn = gr.Button(value="Submit")
-    btn.click(news_and_analysis, inputs=topic, outputs= gr.Dataframe())
+    analyze_btn.click(
+        news_and_analysis,
+        inputs=[topic],
+        outputs=[news_output, sentiment_plot]
+    )
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()