How to Scrape Crunchbase: Startup Funding and Investor Data

Crunchbase is the go-to database for startup funding data. Whether you're a VC analyst or founder doing competitive research, Crunchbase data is invaluable.

Using Crunchbase's API

import requests

class CrunchbaseScraper:
    def __init__(self, api_key):
        self.key = api_key
        self.base = 'https://api.crunchbase.com/api/v4'
        self.headers = {'X-cb-user-key': self.key}

    def search(self, query, limit=25):
        resp = requests.get(f'{self.base}/autocompletes',
            headers=self.headers,
            params={'query': query, 'collection_ids': 'organizations', 'limit': limit})
        return [{
            'name': e['identifier']['value'],
            'permalink': e['identifier']['permalink']
        } for e in resp.json().get('entities', [])]

    def get_org(self, permalink):
        resp = requests.get(f'{self.base}/entities/organizations/{permalink}',
            headers=self.headers,
            params={'field_ids': ['short_description', 'founded_on', 'funding_total', 'website_url']})
        p = resp.json().get('properties', {})
        return {
            'description': p.get('short_description'),
            'founded': p.get('founded_on'),
            'funding': p.get('funding_total', {}),
            'website': p.get('website_url')
        }

Scraping Funding Rounds

class FundingScraper:
    def __init__(self, api_key):
        self.key = api_key
        self.base = 'https://api.crunchbase.com/api/v4'
        self.headers = {'X-cb-user-key': self.key}

    def get_rounds(self, permalink):
        resp = requests.get(
            f'{self.base}/entities/organizations/{permalink}/funding_rounds',
            headers=self.headers,
            params={'field_ids': ['announced_on', 'money_raised', 'investment_type', 'investor_identifiers']})
        rounds = []
        for item in resp.json().get('entities', []):
            p = item.get('properties', {})
            money = p.get('money_raised', {})
            rounds.append({
                'date': p.get('announced_on'),
                'type': p.get('investment_type'),
                'amount': money.get('value'),
                'investors': [i.get('value') for i in p.get('investor_identifiers', [])]
            })
        return sorted(rounds, key=lambda x: x['date'] or '', reverse=True)

    def recent_rounds(self, min_amount=1000000):
        resp = requests.post(f'{self.base}/searches/funding_rounds',
            headers=self.headers, json={
                'field_ids': ['announced_on', 'money_raised', 'funded_organization_identifier'],
                'order': [{'field_id': 'announced_on', 'sort': 'desc'}],
                'query': [{'type': 'predicate', 'field_id': 'money_raised',
                    'operator_id': 'gte', 'values': [{'value': min_amount, 'currency': 'USD'}]}],
                'limit': 50
            })
        return [{
            'company': e['properties'].get('funded_organization_identifier', {}).get('value'),
            'date': e['properties'].get('announced_on'),
            'amount': e['properties'].get('money_raised', {}).get('value')
        } for e in resp.json().get('entities', [])]

Investor Portfolio Tracker

class InvestorTracker:
    def __init__(self, api_key):
        self.key = api_key
        self.base = 'https://api.crunchbase.com/api/v4'
        self.headers = {'X-cb-user-key': self.key}

    def portfolio(self, permalink):
        resp = requests.get(
            f'{self.base}/entities/organizations/{permalink}/participated_investments',
            headers=self.headers,
            params={'field_ids': ['organization_identifier', 'announced_on']})
        return [{
            'company': i['properties'].get('organization_identifier', {}).get('value'),
            'date': i['properties'].get('announced_on')
        } for i in resp.json().get('entities', [])]

    def find_coinvestments(self, permalinks):
        portfolios = {p: set(i['company'] for i in self.portfolio(p) if i['company']) for p in permalinks}
        for i, p1 in enumerate(permalinks):
            for p2 in permalinks[i+1:]:
                shared = portfolios[p1] & portfolios[p2]
                if shared: print(f"{p1} & {p2} co-invested in: {shared}")

Data Export

import pandas as pd

def export_report(rounds, filename='funding.csv'):
    df = pd.DataFrame(rounds)
    if 'amount' in df.columns:
        df['amount_m'] = df['amount'].apply(lambda x: round(x/1e6, 2) if x else None)
    df.to_csv(filename, index=False)
    print(f"Exported {len(df)} rounds")

Scaling

ScraperAPI manages proxy rotation. ThorData provides residential proxies, and ScrapeOps monitors pipelines.

Conclusion

Start with the official API, respect rate limits, and build incrementally for comprehensive startup ecosystem intelligence.