# web_summarizer_app.py

import os
import gradio as gr
import requests
from bs4 import BeautifulSoup
from dotenv import load_dotenv
# Import the Google Generative AI library
import google.generativeai as genai

# Load environment variables
load_dotenv()
# Get the Gemini API key
gemini_api_key = os.getenv("GEMINI_API_KEY")

# Configure the generative AI model
# Ensure GEMINI_API_KEY is set in your .env file
if not gemini_api_key:
    raise ValueError("GEMINI_API_KEY environment variable not set.")

genai.configure(api_key=gemini_api_key)

# Use the specified Gemini model
# You can change 'gemini-1.5-flash-latest' if needed, but the user requested 1.5 Flash
model_name = os.getenv("GEMINI_MODEL", "gemini-1.5-flash-latest")
model = genai.GenerativeModel(model_name)


# 🌐 Web Scraper
def scrape_text_from_url(url):
    """
    Scrapes visible text content from a given URL.
    Limits the text length to 5000 characters to avoid large inputs.
    """
    try:
        response = requests.get(url, timeout=10)
        # Raise an exception for bad status codes (4xx or 5xx)
        response.raise_for_status()
        soup = BeautifulSoup(response.content, "html.parser")

        # Remove scripts and style tags
        for tag in soup(["script", "style"]):
            tag.decompose()

        # Extract visible text and join into a single string
        text = " ".join(chunk.strip() for chunk in soup.stripped_strings)
        return text[:5000]  # limit to avoid token overflow
    except requests.exceptions.RequestException as e:
        return f"❌ Error fetching the page: {str(e)}"
    except Exception as e:
        return f"❌ An unexpected error occurred during scraping: {str(e)}"

# 🧠 LLM Summarizer (using Gemini)
def summarize_with_gemini(text):
    """
    Summarizes the provided text using the configured Gemini model.
    """
    if not text or "❌" in text:
        return "Cannot summarize due to scraping error or empty text."

    try:
        # Use the generate_content method for Gemini
        response = model.generate_content(f"Please summarize the following content:\n\n{text}")
        # Access the text content from the response
        return response.text.strip()
    except Exception as e:
        return f"❌ Error from Gemini API: {str(e)}"

# 🔁 Combined Function
def scrape_and_summarize(url):
    """
    Combines scraping and summarizing functionalities.
    """
    raw_text = scrape_text_from_url(url)
    # Check if scraping failed before attempting summarization
    if "❌" in raw_text:
        return raw_text, "Summarization skipped due to scraping error."

    summary = summarize_with_gemini(raw_text)
    return raw_text, summary

# 🎨 Gradio UI
with gr.Blocks(title="🔎 Web Summarizer with AI") as demo:
    gr.Markdown("## 🧠🌐 Web Article Summarizer")
    gr.Markdown("Enter a webpage URL below. The AI will scrape and summarize the content using Gemini 1.5 Flash.")

    with gr.Row():
        url_input = gr.Textbox(label="🔗 Enter URL", placeholder="https://example.com", scale=4)
        btn = gr.Button("Summarize", variant="primary")

    with gr.Row():
        with gr.Column(scale=1):
            raw_output = gr.Textbox(label="📝 Raw Scraped Text", lines=15, interactive=False)
        with gr.Column(scale=1):
            summary_output = gr.Textbox(label="📄 AI Summary", lines=15, interactive=False)

    # Link the button click event to the combined function
    btn.click(scrape_and_summarize, inputs=[url_input], outputs=[raw_output, summary_output])

# 🚀 Launch app
if __name__ == "__main__":
    # You can set share=True to create a public link (be cautious with API keys)
    demo.launch()