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

# Download once
nltk.download('punkt')
nltk.download('stopwords')

def fetch_text(url):
    try:
        headers = {"User-Agent": "Mozilla/5.0"}
        response = requests.get(url, headers=headers, timeout=5)
        response.raise_for_status()

        soup = BeautifulSoup(response.text, 'html.parser')

        # Only extract <p> tag text for speed & relevance
        paragraphs = soup.find_all('p')
        text = ' '.join([p.get_text() for p in paragraphs])

        if not text.strip():
            return None, f"No readable <p> content found at {url}"
        return text, None
    except Exception as e:
        return None, f"Error fetching {url}: {str(e)}"

def extract_keywords(text):
    text = text.lower()
    tokens = word_tokenize(text)
    words = [w for w in tokens if w.isalnum()]
    stop_words = set(stopwords.words('english'))
    return set([w for w in words if w not in stop_words and len(w) > 2])

def compare_keywords(url_a, url_b):
    text_a, error_a = fetch_text(url_a)
    text_b, error_b = fetch_text(url_b)

    if error_a or error_b:
        return f"❌ Errors:\n\n{error_a or ''}\n{error_b or ''}"

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

    missing = sorted(list(keywords_b - keywords_a))

    if not missing:
        return "✅ No unique keywords found in B that are missing in A."
    
    return f"🔍 Keywords in B but not A:\n\n" + "\n".join(missing)

# Gradio interface
demo = gr.Interface(
    fn=compare_keywords,
    inputs=[
        gr.Textbox(label="Your Website (A)"),
        gr.Textbox(label="Competitor Website (B)")
    ],
    outputs="text",
    title="🔑 Website Keyword Gap Finder",
    description="Enter two URLs. See what keywords your competitor uses that you don't."
)

demo.launch()