Upload 3 files

.env

@@ -0,0 +1,3 @@
+GROQ_API_KEY=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
+BRIGHT_API_KEY=ded1bc00-4d84-4dee-b4d6-c896cadf2417
+BRIGHT_ZONE=web_unlocker2

app.py

@@ -1,69 +1,186 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+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 gr.update(value=[]), 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):
+            url_input = gr.Textbox(
+                label="🔗 Goodreads URL",
+                placeholder="Paste a Goodreads list URL here..."
+            )
+
+            scrape_btn = gr.Button("📥 Scrape 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()

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+requests
+beautifulsoup4
+pandas
+groq
+python-dotenv