Spaces:
Sleeping
Sleeping
| import logging | |
| from bs4 import BeautifulSoup | |
| import requests | |
| import nltk | |
| from transformers import pipeline | |
| import gradio as gr | |
| from newsapi import NewsApiClient # Import NewsApiClient from newsapi library | |
| # Configure logging | |
| logging.basicConfig(level=logging.DEBUG) | |
| # Initialize the summarization pipeline from Hugging Face Transformers | |
| summarizer = pipeline("summarization") | |
| # Initialize the NLTK sentence tokenizer | |
| nltk.download('punkt') | |
| # Initialize the News API client with your API key | |
| newsapi = NewsApiClient(api_key='your_newsapi_key_here') | |
| # Function to fetch content from a given URL | |
| def fetch_article_content(url): | |
| try: | |
| r = requests.get(url) | |
| soup = BeautifulSoup(r.text, 'html.parser') | |
| results = soup.find_all(['h1', 'p']) | |
| text = [result.text for result in results] | |
| return ' '.join(text) | |
| except Exception as e: | |
| logging.error(f"Error fetching content from {url}: {e}") | |
| return "" | |
| # Function to summarize news articles based on a query | |
| def summarize_news(query, num_results=3): | |
| logging.debug(f"Query received: {query}") | |
| logging.debug(f"Number of results requested: {num_results}") | |
| # Search for news articles | |
| logging.debug("Searching for news articles...") | |
| articles = [] | |
| aggregated_content = "" | |
| try: | |
| news_results = newsapi.get_everything(q=query, language='en', page_size=num_results) | |
| logging.debug(f"Search results: {news_results}") | |
| for article in news_results['articles']: | |
| url = article['url'] | |
| logging.debug(f"Fetching content from URL: {url}") | |
| content = fetch_article_content(url) | |
| aggregated_content += content + " " | |
| except Exception as e: | |
| logging.error(f"Error fetching news articles: {e}") | |
| # Summarize the aggregated content | |
| try: | |
| # Chunk the aggregated content into meaningful segments | |
| sentences = nltk.sent_tokenize(aggregated_content) | |
| # Summarize each sentence individually if it's meaningful | |
| summaries = [] | |
| for sentence in sentences: | |
| if len(sentence) > 10: # Adjust minimum length as needed | |
| summary = summarizer(sentence, max_length=120, min_length=30, do_sample=False) | |
| summaries.append(summary[0]['summary_text']) | |
| # Join all summaries to form final output | |
| final_summary = " ".join(summaries) | |
| logging.debug(f"Final summarized text: {final_summary}") | |
| return final_summary | |
| except Exception as e: | |
| logging.error(f"Error during summarization: {e}") | |
| return "An error occurred during summarization." | |
| # Setting up Gradio interface | |
| iface = gr.Interface( | |
| fn=summarize_news, | |
| inputs=[ | |
| gr.Textbox(label="Query"), | |
| gr.Slider(minimum=1, maximum=10, value=3, label="Number of Results") | |
| ], | |
| outputs="textbox", | |
| title="News Summarizer", | |
| description="Enter a query to get a consolidated summary of the top news articles." | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() | |