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