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

# -------------------------------
# LOAD KEYS
# -------------------------------
load_dotenv()
BRIGHTDATA_API_KEY = os.getenv("BRIGHTDATA_API_KEY")
GROQ_API_KEY = os.getenv("GROQ_API_KEY")

client = Groq(api_key=GROQ_API_KEY)

# ============================================================
# TAB 1: SIMPLE GOODREADS SCRAPER
# ============================================================

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

    data = {
        "zone": "web_unlocker2",
        "url": "https://www.goodreads.com/list/show/1.Best_Books_Ever",
        "format": "raw"
    }

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

    soup = BeautifulSoup(response.text, "html.parser")
    books = soup.select("tr[itemtype='http://schema.org/Book']")

    results = []
    for b in books[:10]:
        try:
            results.append({
                "title": b.select_one("a.bookTitle span").text.strip(),
                "author": b.select_one("a.authorName span").text.strip(),
                "rating": b.select_one("span.minirating").text.strip()
            })
        except:
            pass

    return results


books_data = get_books()


def ask_books(question, history):
    context = str(books_data)

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

    return res.choices[0].message.content


# ============================================================
# TAB 2: SIMPLE YOUTUBE TRANSCRIPT
# ============================================================

current_transcript = ""

def load_transcript(video_id):
    global current_transcript

    try:
        if "youtube.com" in video_id:
            video_id = video_id.split("v=")[-1]
        elif "youtu.be" in video_id:
            video_id = video_id.split("/")[-1]

        data = YouTubeTranscriptApi().fetch(video_id)
        current_transcript = " ".join([x.text for x in data])

        return "✅ Transcript loaded"

    except:
        return "❌ Transcript not available"


def ask_youtube(question, history):
    if not current_transcript:
        return "⚠️ Load transcript first"

    res = client.chat.completions.create(
        model="llama-3.1-8b-instant",
        messages=[
            {"role": "system", "content": f"Answer ONLY from this: {current_transcript[:5000]}"},
            {"role": "user", "content": question}
        ]
    )

    return res.choices[0].message.content


# ============================================================
# UI
# ============================================================

with gr.Blocks() as app:

    gr.Markdown("# 🤖 AI Q&A Bot (Ver 2)")

    with gr.Tabs():

        # TAB 1
        with gr.Tab("📚 Books"):
            gr.Markdown("Ask questions about Goodreads books")

            gr.ChatInterface(
                fn=ask_books,
                examples=[
                    "What is the top book?",
                    "Who wrote second book?"
                ]
            )

        # TAB 2
        with gr.Tab("🎬 YouTube"):
            vid = gr.Textbox(label="Enter YouTube URL or ID")
            status = gr.Textbox(label="Status")

            btn = gr.Button("Load Transcript")
            btn.click(load_transcript, inputs=vid, outputs=status)

            gr.ChatInterface(fn=ask_youtube)

app.launch()