Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import requests | |
| from bs4 import BeautifulSoup | |
| import pandas as pd | |
| from transformers import pipeline | |
| import plotly.express as px | |
| from datetime import datetime, timedelta | |
| # Sentiment Analysis Model | |
| sentiment_model = pipeline(model="finiteautomata/bertweet-base-sentiment-analysis") | |
| # 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 | |
| # 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') | |
| 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) | |
| # Function to perform sentiment analysis | |
| def analyze_sentiment(text): | |
| result = sentiment_model(text)[0] | |
| return result['label'], result['score'] | |
| # Main function to process news and perform analysis | |
| def news_and_analysis(query): | |
| # Fetch news | |
| news_df = fetch_news(query) | |
| 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 = px.bar( | |
| news_df, | |
| x='Time', | |
| y='Sentiment_Score', | |
| color='Sentiment', | |
| color_discrete_map={'positive': 'green', 'neutral': 'gray', 'negative': 'red'}, | |
| title='News Sentiment Over Time', | |
| labels={'Time': 'Publication Time', 'Sentiment_Score': 'Sentiment Score'} | |
| ) | |
| return news_df, sentiment_fig | |
| # Gradio interface | |
| with gr.Blocks() as demo: | |
| gr.Markdown( | |
| """ | |
| # Financial News Sentiment Analysis | |
| Analyze the sentiment of news articles related to financial topics or companies. | |
| Enter a topic or company name to get started. | |
| """ | |
| ) | |
| with gr.Row(): | |
| with gr.Column(): | |
| topic = gr.Textbox(label="Enter a financial topic or company name", placeholder="e.g., Apple Inc.") | |
| analyze_btn = gr.Button(value="Analyze") | |
| with gr.Column(): | |
| news_output = gr.DataFrame(label="News and Sentiment Analysis") | |
| sentiment_plot = gr.Plot(label="Sentiment Analysis") | |
| analyze_btn.click( | |
| news_and_analysis, | |
| inputs=[topic], | |
| outputs=[news_output, sentiment_plot] | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() | |