import gradio as gr
from transformers import pipeline
from bs4 import BeautifulSoup
import requests
from googlesearch import search

def summarize_news(query):
    # Initialize summarization pipeline
    summarizer = pipeline("summarization")

    # Search for news articles
    search_results = search(query, num_results=3)
    articles = []
    
    for url in search_results:
        try:
            # Fetch the content of the news article
            r = requests.get(url)
            soup = BeautifulSoup(r.text, 'html.parser')
            results = soup.find_all(['h1', 'p'])
            text = [result.text for result in results]
            ARTICLE = ' '.join(text)

            # Chunk the article text
            max_chunk = 500
            ARTICLE = ARTICLE.replace('.', '.<eos>')
            ARTICLE = ARTICLE.replace('?', '?<eos>')
            ARTICLE = ARTICLE.replace('!', '!<eos>')

            sentences = ARTICLE.split('<eos>')
            current_chunk = 0
            chunks = []
            for sentence in sentences:
                if len(chunks) == current_chunk + 1:
                    if len(chunks[current_chunk]) + len(sentence.split(' ')) <= max_chunk:
                        chunks[current_chunk].extend(sentence.split(' '))
                    else:
                        current_chunk += 1
                        chunks.append(sentence.split(' '))
                else:
                    chunks.append(sentence.split(' '))

            for chunk_id in range(len(chunks)):
                chunks[chunk_id] = ' '.join(chunks[chunk_id])

            # Summarize the chunks
            summaries = summarizer(chunks, max_length=120, min_length=30, do_sample=False)
            summary_text = " ".join([summary['summary_text'] for summary in summaries])
            articles.append((url, summary_text))
        except Exception as e:
            continue

    return articles

def format_output(articles):
    formatted_text = ""
    for url, summary in articles:
        formatted_text += f"URL: {url}\nSummary: {summary}\n\n"
    return formatted_text

iface = gr.Interface(
    fn=lambda query: format_output(summarize_news(query)), 
    inputs="text", 
    outputs="text",
    title="News Summarizer",
    description="Enter a query to get summarized versions of the top news articles."
)

iface.launch()