app3.py

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

# Function to scrape Crunchbase for companies matching the description
def scrape_crunchbase(description):
    # Simulate a search query on Crunchbase
    search_url = f"https://www.crunchbase.com/textsearch?q={description}"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
    }
    response = requests.get(search_url, headers=headers)
    soup = BeautifulSoup(response.content, 'html.parser')
    
    # Extract company details
    companies = []
    for item in soup.find_all('div', class_='result-info'):  # Adjust based on Crunchbase's HTML structure
        company_name = item.find('a', class_='result-name').text.strip()
        company_url = "https://www.crunchbase.com" + item.find('a', class_='result-name')['href']
        
        # Fetch additional details from the company's Crunchbase page
        company_response = requests.get(company_url, headers=headers)
        company_soup = BeautifulSoup(company_response.content, 'html.parser')
        
        # Extract relevant fields
        short_description = company_soup.find('meta', attrs={'name': 'description'})['content'] if company_soup.find('meta', attrs={'name': 'description'}) else 'N/A'
        founded_on = company_soup.find('span', text='Founded').find_next('span').text.strip() if company_soup.find('span', text='Founded') else 'N/A'
        ipo_status = company_soup.find('span', text='IPO Status').find_next('span').text.strip() if company_soup.find('span', text='IPO Status') else 'N/A'
        contact_email = company_soup.find('a', href=lambda href: href and 'mailto:' in href)['href'].replace('mailto:', '') if company_soup.find('a', href=lambda href: href and 'mailto:' in href) else 'N/A'
        legal_name = company_soup.find('span', text='Legal Name').find_next('span').text.strip() if company_soup.find('span', text='Legal Name') else 'N/A'
        website = company_soup.find('a', href=lambda href: href and 'http' in href)['href'] if company_soup.find('a', href=lambda href: href and 'http' in href) else 'N/A'
        city = company_soup.find('span', text='City').find_next('span').text.strip() if company_soup.find('span', text='City') else 'N/A'
        region = company_soup.find('span', text='Region').find_next('span').text.strip() if company_soup.find('span', text='Region') else 'N/A'
        country = company_soup.find('span', text='Country').find_next('span').text.strip() if company_soup.find('span', text='Country') else 'N/A'
        continent = company_soup.find('span', text='Continent').find_next('span').text.strip() if company_soup.find('span', text='Continent') else 'N/A'
        rank_org_company = company_soup.find('span', text='Rank Org Company').find_next('span').text.strip() if company_soup.find('span', text='Rank Org Company') else 'N/A'
        operating_status = company_soup.find('span', text='Operating Status').find_next('span').text.strip() if company_soup.find('span', text='Operating Status') else 'N/A'
        last_funding_type = company_soup.find('span', text='Last Funding Type').find_next('span').text.strip() if company_soup.find('span', text='Last Funding Type') else 'N/A'
        total_rounds = company_soup.find('span', text='Total Rounds').find_next('span').text.strip() if company_soup.find('span', text='Total Rounds') else 'N/A'
        total_investors = company_soup.find('span', text='Total Investors').find_next('span').text.strip() if company_soup.find('span', text='Total Investors') else 'N/A'
        total_money_raised_usd = company_soup.find('span', text='Total Money Raised USD').find_next('span').text.strip() if company_soup.find('span', text='Total Money Raised USD') else 'N/A'
        last_round_money_raised_usd = company_soup.find('span', text='Last Round Money Raised USD').find_next('span').text.strip() if company_soup.find('span', text='Last Round Money Raised USD') else 'N/A'
        most_recent_funding_date = company_soup.find('span', text='Most Recent Funding Date').find_next('span').text.strip() if company_soup.find('span', text='Most Recent Funding Date') else 'N/A'
        industries = company_soup.find('span', text='Industries').find_next('span').text.strip() if company_soup.find('span', text='Industries') else 'N/A'
        similar_companies_permalinks = company_soup.find('span', text='Similar Companies Permalinks').find_next('span').text.strip() if company_soup.find('span', text='Similar Companies Permalinks') else 'N/A'
        min_employees = company_soup.find('span', text='Min Employees').find_next('span').text.strip() if company_soup.find('span', text='Min Employees') else 'N/A'
        max_employees = company_soup.find('span', text='Max Employees').find_next('span').text.strip() if company_soup.find('span', text='Max Employees') else 'N/A'
        max_score = company_soup.find('span', text='Max Score').find_next('span').text.strip() if company_soup.find('span', text='Max Score') else 'N/A'
        
        # Add company details to the list
        companies.append({
            'Url': company_url,
            'Company Name': company_name,
            'Short Description': short_description,
            'Founded On': founded_on,
            'Ipo Status': ipo_status,
            'Contact Email': contact_email,
            'Legal Name': legal_name,
            'Website': website,
            'City': city,
            'Region': region,
            'Country': country,
            'Continent': continent,
            'Rank Org Company': rank_org_company,
            'Operating Status': operating_status,
            'Last Funding Type': last_funding_type,
            'Total Rounds': total_rounds,
            'Total Investors': total_investors,
            'Total Money Raised USD': total_money_raised_usd,
            'Last Round Money Raised USD': last_round_money_raised_usd,
            'Most Recent Funding Date': most_recent_funding_date,
            'Industries': industries,
            'Similar Companies Permalinks': similar_companies_permalinks,
            'Min Employees': min_employees,
            'Max Employees': max_employees,
            'Max Score': max_score
        })
    
    # Convert the list to a DataFrame
    df = pd.DataFrame(companies)
    return df.head(5)  # Return the top 5 companies

# Gradio Interface
def gradio_interface(description):
    df = scrape_crunchbase(description)
    return df

# Launch Gradio App
iface = gr.Interface(
    fn=gradio_interface,
    inputs="text",
    outputs="dataframe",
    title="Crunchbase Company Search",
    description="Enter a company services description to find the top 5 matching companies on Crunchbase."
)

iface.launch()