app.py

import requests
from bs4 import BeautifulSoup
import pandas as pd
import time
from cryptography.fernet import Fernet
import gradio as gr

BASE_URL = "http://books.toscrape.com/catalogue/page-{}.html"

# Scrape a single page
def scrape_page(page):
    books = []
    url = BASE_URL.format(page)
    response = requests.get(url, headers={"User-Agent": "Mozilla/5.0"})
    if response.status_code != 200:
        return books
    soup = BeautifulSoup(response.text, "html.parser")
    for book in soup.select("article.product_pod"):
        title = book.h3.a['title']
        price = book.select_one("p.price_color").text
        rating = book.p['class'][1]  # e.g., 'Three'
        books.append({"Title": title, "Price": price, "Rating": rating})
    return books

# Scrape multiple pages
def scrape_books(pages=1):
    all_books = []
    for page in range(1, pages+1):
        all_books.extend(scrape_page(page))
        time.sleep(1)  # ethical scraping
    df = pd.DataFrame(all_books)
    return df

# Mask titles (original title removed)
def mask_titles_only(df):
    df_masked = df.copy()
    df_masked["Title"] = df_masked["Title"].apply(lambda x: x[0] + "***" if x != "N/A" else x)
    return df_masked

# Encrypt CSV
def encrypt_csv(df):
    key = Fernet.generate_key()
    cipher = Fernet(key)
    csv_bytes = df.to_csv(index=False).encode()
    encrypted_file = "books_encrypted.csv"
    with open(encrypted_file, "wb") as f:
        f.write(cipher.encrypt(csv_bytes))
    return encrypted_file, key.decode()

# Gradio interface function
def app_interface(pages, security_option):
    df = scrape_books(pages)
    
    if security_option == "Mask Titles":
        df = mask_titles_only(df)
        file_path = "books_masked.csv"
        df.to_csv(file_path, index=False)
        return df, file_path, "Masked CSV ready to download."
    elif security_option == "Encrypt CSV":
        encrypted_file, key = encrypt_csv(df)
        return df, encrypted_file, f"Encrypted CSV ready to download. Key: {key}"
    else:
        file_path = "books.csv"
        df.to_csv(file_path, index=False)
        return df, file_path, "CSV ready to download."

# Gradio App
iface = gr.Interface(
    fn=app_interface,
    inputs=[
        gr.Slider(1, 50, step=1, label="Number of Pages to Scrape", value=1),
        gr.Radio(["None", "Mask Titles", "Encrypt CSV"], label="Security Option")
    ],
    outputs=[
        gr.Dataframe(label="Books Data"),
        gr.File(label="Download CSV File"),
        gr.Textbox(label="Info / Encryption Key")
    ],
    title="Secure Book Scraper",
    description="Scrape book details from 'Books to Scrape'. Mask book titles or encrypt the CSV for secure storage."
)

iface.launch()