app.py

import gradio as gr
import requests
from bs4 import BeautifulSoup
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
import string

nltk.download('punkt')
nltk.download('stopwords')

def get_text_from_url(url):
    try:
        response = requests.get(url, timeout=10)
        soup = BeautifulSoup(response.text, 'html.parser')
        text = soup.get_text()
        return text
    except:
        return ""

def extract_keywords(text):
    text = text.lower()
    tokens = word_tokenize(text)
    words = [word for word in tokens if word.isalnum()]
    stop_words = set(stopwords.words('english'))
    keywords = [word for word in words if word not in stop_words]
    return set(keywords)

def compare_keywords(url_a, url_b):
    text_a = get_text_from_url(url_a)
    text_b = get_text_from_url(url_b)

    if not text_a or not text_b:
        return "❌ Failed to fetch one or both websites. Please check URLs."

    keywords_a = extract_keywords(text_a)
    keywords_b = extract_keywords(text_b)

    diff_keywords = keywords_b - keywords_a

    sorted_keywords = sorted(diff_keywords)
    return "\n".join(sorted_keywords)

interface = gr.Interface(
    fn=compare_keywords,
    inputs=[
        gr.Textbox(label="Your Website (A)"),
        gr.Textbox(label="Competitor Website (B)")
    ],
    outputs="text",
    title="🔍 Competitor Keyword Finder",
    description="Enter your website and a competitor's. This tool finds keywords the competitor uses but you don’t."
)

interface.launch()