Spaces:
Sleeping
Sleeping
| import requests | |
| from bs4 import BeautifulSoup | |
| from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification | |
| from deep_translator import GoogleTranslator | |
| from scipy.special import softmax | |
| import gtts | |
| import os | |
| # Initialize HuggingFace sentiment model | |
| MODEL_NAME = "cardiffnlp/twitter-roberta-base-sentiment" | |
| tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) | |
| sentiment_model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME) | |
| # Initialize summarizer | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") | |
| # News API details | |
| NEWS_API_KEY = "7e72763bebb54fd79cb632390738cbb1" | |
| NEWS_API_URL = "https://newsapi.org/v2/everything" | |
| # Function to fetch news articles | |
| def fetch_news(company): | |
| params = { | |
| "q": company, | |
| "apiKey": NEWS_API_KEY, | |
| "language": "en", | |
| "sortBy": "relevancy", | |
| "pageSize": 10 | |
| } | |
| response = requests.get(NEWS_API_URL, params=params) | |
| data = response.json() | |
| articles = [] | |
| if "articles" in data: | |
| for item in data["articles"]: | |
| full_text = scrape_article_text(item["url"]) | |
| summary = summarize_text(full_text) if full_text else "No summary available." | |
| articles.append({ | |
| "title": item["title"], | |
| "summary": summary, | |
| "link": item["url"], | |
| "published_at": item["publishedAt"], | |
| "source": item["source"]["name"] | |
| }) | |
| return articles | |
| # Function to scrape full article text from a URL | |
| def scrape_article_text(url): | |
| try: | |
| headers = {"User-Agent": "Mozilla/5.0"} | |
| response = requests.get(url, headers=headers, timeout=10) | |
| soup = BeautifulSoup(response.text, "html.parser") | |
| paragraphs = soup.find_all("p") | |
| full_text = " ".join(p.text for p in paragraphs) | |
| return full_text | |
| except Exception: | |
| return "" | |
| # Function to summarize text using BART model | |
| def summarize_text(text, sentences_count=3): | |
| if not text.strip(): | |
| return "No summary available." | |
| # Truncate long text to avoid input limit issues | |
| text = text[:1024] | |
| summary = summarizer(text, max_length=130, min_length=30, do_sample=False) | |
| return summary[0]['summary_text'] | |
| # Function to analyze sentiment | |
| def analyze_sentiment(text): | |
| encoded_text = tokenizer(text, return_tensors='pt') | |
| output = sentiment_model(**encoded_text) | |
| scores = output.logits[0].detach().numpy() | |
| scores = softmax(scores) | |
| sentiment_labels = {0: 'Negative', 1: 'Neutral', 2: 'Positive'} | |
| sentiment = sentiment_labels[scores.argmax()] | |
| return sentiment | |
| # Translate text to Hindi | |
| def translate_to_hindi(text): | |
| return GoogleTranslator(source='en', target='hi').translate(text) | |
| # Convert headline to speech in Hindi | |
| def text_to_speech(text, filename="news_headline.mp3"): | |
| if not text.strip(): | |
| return None | |
| hindi_text = translate_to_hindi(text) | |
| tts = gtts.gTTS(text=hindi_text, lang='hi') | |
| tts.save(filename) | |
| return filename | |