app.py

import requests
from bs4 import BeautifulSoup
import os
from dotenv import load_dotenv
from groq import Groq
import gradio as gr

# -------------------------------
# LOAD API KEYS
# -------------------------------
load_dotenv()

BRIGHTDATA_API_KEY = os.getenv("BRIGHTDATA_API_KEY")
GROQ_API_KEY = os.getenv("GROQ_API_KEY")

# -------------------------------
# GROQ CLIENT
# -------------------------------
client = Groq(api_key=GROQ_API_KEY)

# -------------------------------
# SCRAPER FUNCTION (DYNAMIC URL)
# -------------------------------
def scrape_books(url):
    if not url:
        return [], "❌ Please enter a URL"

    headers = {
        "Authorization": f"Bearer {BRIGHTDATA_API_KEY}",
        "Content-Type": "application/json"
    }

    data = {
        "zone": "web_unlocker1",
        "url": url,
        "format": "raw"
    }

    try:
        response = requests.post(
            "https://api.brightdata.com/request",
            json=data,
            headers=headers,
            timeout=30
        )

        if response.status_code != 200:
            return [], f"❌ Failed! Status: {response.status_code}"

        soup = BeautifulSoup(response.text, "html.parser")

        books = soup.select("tr[itemtype='http://schema.org/Book']")
        results = []

        for book in books[:10]:
            try:
                title = book.select_one("a.bookTitle span").text.strip()
                author = book.select_one("a.authorName span").text.strip()
                rating = book.select_one("span.minirating").text.strip()

                results.append({
                    "title": title,
                    "author": author,
                    "rating": rating
                })
            except:
                pass

        if not results:
            return [], "⚠️ No books found (page structure changed?)"

        return results, f"✅ Found {len(results)} books"

    except Exception as e:
        return [], f"❌ Error: {str(e)}"


# -------------------------------
# GLOBAL STORAGE
# -------------------------------
books_data = []

# -------------------------------
# LOAD DATA BUTTON FUNCTION
# -------------------------------
def load_data(url):
    global books_data
    books_data, status = scrape_books(url)
    return status


# -------------------------------
# AI FUNCTION
# -------------------------------
def ask_ai(message, history):
    if not books_data:
        return "⚠️ Please load data first using URL"

    context = str(books_data)

    try:
        response = client.chat.completions.create(
            model="llama-3.1-8b-instant",
            messages=[
                {
                    "role": "system",
                    "content": f"Answer ONLY using this data: {context}"
                },
                {"role": "user", "content": message}
            ]
        )

        return response.choices[0].message.content

    except Exception as e:
        return f"❌ AI Error: {str(e)}"


# -------------------------------
# UI (GRADIO)
# -------------------------------
with gr.Blocks() as demo:

    gr.Markdown("""
        ### 🔗 Example URL (Copy & Paste):
        👉 https://www.goodreads.com/list/show/1.Best_Books_Ever
    """)

    url_input = gr.Textbox(
        label="Enter Goodreads URL",
        placeholder="Paste URL here..."
    )

    load_btn = gr.Button("Load Data")
    status_output = gr.Textbox(label="Status")

    load_btn.click(fn=load_data, inputs=url_input, outputs=status_output)

    # Chat
    gr.ChatInterface(
        fn=ask_ai,
        title="Ask Questions",
        description="Ask about the scraped books"
    )

demo.launch()