app.py

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

load_dotenv()

GROQ_API_KEY = os.getenv("GROQ_API_KEY")
BRIGHT_API_KEY = os.getenv("BRIGHT_API_KEY")
BRIGHT_ZONE = os.getenv("BRIGHT_ZONE")

client = Groq(api_key=GROQ_API_KEY)

# -------------------------------
# BRIGHT DATA WEB UNLOCKER
# -------------------------------

def brightdata_request(target_url):
    try:
        response = requests.post(
            "https://api.brightdata.com/request",
            headers={
                "Content-Type": "application/json",
                "Authorization": f"Bearer {BRIGHT_API_KEY}"
            },
            json={
                "zone": BRIGHT_ZONE,
                "url": target_url,
                "format": "raw"
            },
            timeout=60
        )

        response.raise_for_status()
        return response.text

    except Exception as e:
        return f"ERROR: {str(e)}"


# -------------------------------
# SCRAPER
# -------------------------------

def scrape_goodreads(url):
    html = brightdata_request(url)

    if html.startswith("ERROR"):
        return [], html

    soup = BeautifulSoup(html, "html.parser")
    books = []

    rows = soup.find_all("tr")

    for row in rows:
        title_tag = row.find("a", class_="bookTitle")
        author_tag = row.find("a", class_="authorName")
        rating_tag = row.find("span", class_="minirating")

        if title_tag and author_tag and rating_tag:
            books.append({
                "title": title_tag.get_text(strip=True),
                "author": author_tag.get_text(strip=True),
                "rating": rating_tag.get_text(strip=True)
            })

    if not books:
        return [], "No books found. Make sure the URL is a Goodreads list page."

    return books[:10], None


# -------------------------------
# AI Q&A
# -------------------------------

def qa_bot(url, question):
    books, error = scrape_goodreads(url)

    if error:
        return f"❌ {error}"

    context = "\n".join(
        [f"{i+1}. {b['title']} by {b['author']} - {b['rating']}"
         for i, b in enumerate(books)]
    )

    system_prompt = f"""
You are a helpful assistant.

Here is book data scraped from Goodreads:

{context}

Answer questions ONLY using this data.
If the answer is not present, say "The data does not contain that information."
"""

    try:
        response = client.chat.completions.create(
            model="llama-3.1-8b-instant",
            messages=[
                {"role": "system", "content": system_prompt},
                {"role": "user", "content": question}
            ]
        )

        return response.choices[0].message.content

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


# -------------------------------
# UI LOGIC FUNCTIONS
# -------------------------------

def scrape_and_display(url):
    books, error = scrape_goodreads(url)

    if error:
        return [], error

    table_data = [[b["title"], b["author"], b["rating"]] for b in books]

    return table_data, "✅ Successfully scraped top 10 books."


# -------------------------------
# GRADIO UI
# -------------------------------

with gr.Blocks(theme=gr.themes.Soft(), title="Goodreads AI Explorer") as demo:

    gr.Markdown("""
    # 📚 Goodreads AI Explorer  
    Scrape book data from a Goodreads list and ask AI questions about it.
    """)

    with gr.Row():
        with gr.Column(scale=2):

            # ✅ Auto-filled URL textbox
            url_input = gr.Textbox(
                label="🔗 Goodreads URL",
                value="https://www.goodreads.com/list/show/1.Best_Books_Ever",
                placeholder="Paste a Goodreads list URL here..."
            )

            scrape_btn = gr.Button("📥 search Books", variant="primary")

            status_output = gr.Markdown()

            books_table = gr.Dataframe(
                headers=["Title", "Author", "Rating"],
                datatype=["str", "str", "str"],
                interactive=False,
                wrap=True
            )

        with gr.Column(scale=3):

            question_input = gr.Textbox(
                label="💬 Ask a Question",
                placeholder="Which book has the highest rating?"
            )

            ask_btn = gr.Button("🤖 Ask AI", variant="secondary")

            answer_output = gr.Markdown()

    # Button Actions
    scrape_btn.click(
        fn=scrape_and_display,
        inputs=url_input,
        outputs=[books_table, status_output]
    )

    ask_btn.click(
        fn=qa_bot,
        inputs=[url_input, question_input],
        outputs=answer_output
    )

if __name__ == "__main__":
    demo.launch()