Spaces:
Running
Running
| import gradio as gr | |
| from transformers import pipeline | |
| import feedparser | |
| from datetime import datetime, timedelta | |
| import pytz | |
| from bs4 import BeautifulSoup | |
| # Global settings | |
| SUMMARIZER_MODEL = "facebook/bart-large-cnn" | |
| RSS_FETCH_INTERVAL = timedelta(hours=8) | |
| ARTICLE_LIMIT = 5 | |
| # News sources | |
| NEWS_SOURCES = { | |
| "Technology": { | |
| "TheNewYorkTimes": "https://rss.nytimes.com/services/xml/rss/nyt/Technology.xml", | |
| "Reuters": "https://www.reutersagency.com/feed/?best-topics=tech&post_type=best" | |
| }, | |
| "Business": { | |
| "TheNewYorkTimes": "https://rss.nytimes.com/services/xml/rss/nyt/Business.xml", | |
| "Reuters": "https://www.reutersagency.com/feed/?best-topics=business-finance&post_type=best" | |
| }, | |
| "Science": { | |
| "TheNewYorkTimes": "https://rss.nytimes.com/services/xml/rss/nyt/Science.xml" | |
| }, | |
| "World News": { | |
| "TheNewYorkTimes": "https://rss.nytimes.com/services/xml/rss/nyt/World.xml", | |
| "BBC": "http://feeds.bbci.co.uk/news/world/rss.xml", | |
| "CNN": "http://rss.cnn.com/rss/edition_world.rss", | |
| "Reuters": "https://www.reutersagency.com/feed/?taxonomy=best-regions&post_type=best" | |
| }, | |
| "Sports": { | |
| "TheNewYorkTimes": "https://rss.nytimes.com/services/xml/rss/nyt/Sports.xml", | |
| "Reuters": "https://www.reutersagency.com/feed/?best-topics=sports&post_type=best" | |
| }, | |
| "Health": { | |
| "TheNewYorkTimes": "https://rss.nytimes.com/services/xml/rss/nyt/Health.xml", | |
| "Politico": "http://rss.politico.com/healthcare.xml", | |
| "Reuters": "https://www.reutersagency.com/feed/?best-topics=health&post_type=best" | |
| }, | |
| } | |
| # Summarizer initialization | |
| summarizer = pipeline("summarization", model=SUMMARIZER_MODEL, device=-1) | |
| def fetch_rss_news(categories): | |
| articles = [] | |
| cutoff_time = datetime.now(pytz.UTC) - RSS_FETCH_INTERVAL | |
| for category in categories: | |
| for source, url in NEWS_SOURCES.get(category, {}).items(): | |
| try: | |
| feed = feedparser.parse(url) | |
| for entry in feed.entries: | |
| published = datetime(*entry.published_parsed[:6], tzinfo=pytz.UTC) | |
| if published > cutoff_time: | |
| articles.append({ | |
| "title": entry.title, | |
| "description": BeautifulSoup(entry.description, "html.parser").get_text(), | |
| "link": entry.link, | |
| "category": category, | |
| "source": source, | |
| "published": published | |
| }) | |
| except Exception as e: | |
| print(f"Error fetching from {url}: {e}") | |
| articles = sorted(articles, key=lambda x: x["published"], reverse=True)[:ARTICLE_LIMIT] | |
| return articles | |
| def summarize_with_ai(text): | |
| try: | |
| result = summarizer(text, max_length=120, min_length=40, truncation=True) | |
| return result[0]['summary_text'] | |
| except Exception as e: | |
| print(f"AI summarization error: {e}") | |
| return "Summary unavailable." | |
| def summarize_with_free_module(text): | |
| # Simple heuristic summarization: return the first few sentences | |
| return '. '.join(text.split('. ')[:3]) + '...' | |
| def summarize_articles(articles, method="AI Model"): | |
| summaries = [] | |
| summarizer_function = summarize_with_ai if method == "AI Model" else summarize_with_free_module | |
| for article in articles: | |
| try: | |
| summary = summarizer_function(article["description"]) | |
| summaries.append( | |
| "Title: {0} | |
| - Category: {1} | |
| - Source: {2} | |
| - Published: {3} | |
| Summary: {4} | |
| Read more: {5}".format( | |
| article["title"], | |
| article["category"], | |
| article["source"], | |
| article["published"].strftime('%Y-%m-%d %H:%M'), | |
| summary, | |
| article["link"] | |
| ) | |
| ) | |
| except Exception as e: | |
| print(f"Error summarizing article: {e}") | |
| return summaries | |
| # Gradio Interface | |
| def generate_summary(categories, method): | |
| if not categories: | |
| return "Please select at least one category." | |
| articles = fetch_rss_news(categories) | |
| if not articles: | |
| return "No recent articles found." | |
| summaries = summarize_articles(articles, method) | |
| return " | |
| ".join(summaries) | |
| demo = gr.Blocks() | |
| with demo: | |
| gr.Markdown("# AI News Summarizer") | |
| with gr.Row(): | |
| categories = gr.CheckboxGroup(choices=list(NEWS_SOURCES.keys()), label="Select Categories") | |
| method = gr.Dropdown(choices=["AI Model", "Free Module"], label="Summarization Method", value="AI Model") | |
| summarize_button = gr.Button("Generate Summary") | |
| output = gr.Textbox(label="Summarized News", lines=15) | |
| summarize_button.click(generate_summary, inputs=[categories, method], outputs=output) | |
| if __name__ == "__main__": | |
| demo.launch() | |