Crunchbase Scraper: Automated Startup Data and Funding Insights Extraction

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.9",
}

def fetch_crunchbase_company_data(url):
    response = requests.get(url, headers=HEADERS)
    
    if response.status_code != 200:
        print("Failed to fetch page:", response.status_code)
        return None

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

    def extract_text(tag, class_name):
        element = soup.find(tag, class_=class_name)
        return element.text.strip() if element else "N/A"

    company_data = {
        "Company Name": extract_text("h1", "profile-name"),
        "Industry": extract_text("span", "field--industry"),
        "Headquarters": extract_text("span", "field--location"),
        "Total Funding": extract_text("span", "field--funding"),
        "Founded Year": extract_text("span", "field--founded")
    }

    return company_data

# Example Crunchbase company profile URL
crunchbase_url = "https://www.crunchbase.com/organization/example-company"

data = fetch_crunchbase_company_data(crunchbase_url)

# Print extracted data
print(data)