app.py

import gradio as gr
import pandas as pd
import requests
from bs4 import BeautifulSoup
import time

def scrape_yellowpages(keyword, location, pages):

    results = []
    pages = int(pages)

    headers = {
        "User-Agent": "Mozilla/5.0"
    }

    for page in range(1, pages + 1):
        url = f"https://www.yellowpages.com/search?search_terms={keyword}&geo_location_terms={location}&page={page}"

        response = requests.get(url, headers=headers)

        if response.status_code != 200:
            return None, None, "Failed to fetch data."

        soup = BeautifulSoup(response.text, "html.parser")
        listings = soup.find_all("div", class_="result")

        for listing in listings:
            try:
                name = listing.find("a", class_="business-name").text.strip()
            except:
                name = ""

            try:
                phone = listing.find("div", class_="phones").text.strip()
            except:
                phone = ""

            try:
                address = listing.find("div", class_="street-address").text.strip()
            except:
                address = ""

            results.append({
                "Business Name": name,
                "Phone": phone,
                "Address": address
            })

        time.sleep(1)

    if len(results) == 0:
        return None, None, "No results found."

    df = pd.DataFrame(results)
    df.drop_duplicates(inplace=True)

    file_name = "yellowpages_leads.csv"
    df.to_csv(file_name, index=False)

    return df, file_name, "Leads scraped successfully."


with gr.Blocks() as demo:

    gr.Markdown("## Real Business Lead Scraper (YellowPages)")

    keyword_input = gr.Textbox(label="Business Type (e.g. dentist)")
    location_input = gr.Textbox(label="Location (e.g. Chicago)")
    pages_input = gr.Number(value=1, label="Number of Pages (1 page ≈ 30 leads)")

    scrape_button = gr.Button("Scrape Leads")

    output_table = gr.Dataframe()
    download_file = gr.File()
    status_output = gr.Textbox(label="Status")

    scrape_button.click(
        scrape_yellowpages,
        inputs=[keyword_input, location_input, pages_input],
        outputs=[output_table, download_file, status_output]
    )

demo.launch()