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

# Configure logging
logging.basicConfig(level=logging.DEBUG)

def summarize_news(query, num_results=3):
    logging.debug(f"Query received: {query}")
    logging.debug(f"Number of results requested: {num_results}")

    # Initialize summarization pipeline with a specific model
    logging.debug("Initializing summarization pipeline...")
    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")

    # Search for news articles
    logging.debug("Searching for news articles...")
    search_results = search(query, num_results=num_results)
    articles = []

    logging.debug(f"Search results: {search_results}")

    for url in search_results:
        try:
            logging.debug(f"Fetching content from URL: {url}")
            # 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
            logging.debug("Chunking the article text...")
            max_chunk = 350
            ARTICLE = ARTICLE.replace('.', '.<eos>')
            ARTICLE = ARTICLE.replace('?', '?<eos>')
            ARTICLE = ARTICLE.replace('!', '!<eos>')

            sentences = ARTICLE.split('<eos>')
            chunks = []
            current_chunk = []

            for sentence in sentences:
                if len(' '.join(current_chunk + sentence.split())) <= max_chunk:
                    current_chunk.extend(sentence.split())
                else:
                    chunks.append(' '.join(current_chunk))
                    current_chunk = sentence.split()
            chunks.append(' '.join(current_chunk))

            logging.debug(f"Chunks created: {chunks}")

            # Summarize the chunks
            logging.debug("Summarizing the chunks...")
            summaries = []
            for chunk in chunks:
                summaries.append(summarizer(chunk, max_length=150, min_length=30, do_sample=False)[0]['summary_text'])
            
            # Concatenate summaries and summarize again for cohesion
            combined_summary = ' '.join(summaries)
            final_summary = summarizer(combined_summary, max_length=300, min_length=80, do_sample=False)[0]['summary_text']
            articles.append((url, final_summary))

            logging.debug(f"Final summary for URL {url}: {final_summary}")
        except Exception as e:
            logging.error(f"Error processing URL {url}: {e}")
            continue

    logging.debug(f"Final summarized articles: {articles}")
    return format_output(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=summarize_news,
    inputs=["textbox", "slider"],
    outputs="textbox",
    title="News Summarizer",
    description="Enter a query to get summarized versions of the top news articles."
)

if __name__ == "__main__":
    logging.debug("Launching Gradio interface...")
    iface.launch()