Crunchbase Scraper
Pricing
Pay per usage
Go to Apify Store
Crunchbase Scraper
Scrape Crunchbase company profiles, funding rounds, founders/executives, and investor data. Search by keyword, industry, location, or funding stage.
Crunchbase Scraper
Pricing
Pay per usage
Scrape Crunchbase company profiles, funding rounds, founders/executives, and investor data. Search by keyword, industry, location, or funding stage.
You can access the Crunchbase Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "tJcVu4kDYQ6M43nOy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/magicfingers~crunchbase-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-magicfingers-crunchbase-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/magicfingers~crunchbase-scraper/runs": { "post": { "operationId": "runs-sync-magicfingers-crunchbase-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/magicfingers~crunchbase-scraper/run-sync": { "post": { "operationId": "run-sync-magicfingers-crunchbase-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "action" ], "properties": { "action": { "title": "Action", "enum": [ "searchCompanies", "scrapeProfiles", "scrapeInvestors", "scrapePeople" ], "type": "string", "description": "What type of scraping to perform.", "default": "searchCompanies" }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Keyword to search for companies/organizations (e.g., 'artificial intelligence', 'fintech')." }, "location": { "title": "Location Filter", "type": "string", "description": "Filter by headquarters location (e.g., 'San Francisco', 'United States', 'Europe')." }, "industryFilter": { "title": "Industry Filter", "type": "string", "description": "Filter by industry category (e.g., 'Artificial Intelligence', 'Financial Services', 'Health Care')." }, "fundingStage": { "title": "Funding Stage Filter", "enum": [ "", "seed", "early_stage_venture", "late_stage_venture", "private_equity", "debt_financing", "post_ipo_equity", "post_ipo_debt", "secondary_market", "grant", "ipo" ], "type": "string", "description": "Filter by last funding stage.", "default": "" }, "directUrls": { "title": "Direct URLs", "type": "array", "description": "List of Crunchbase URLs to scrape directly (for scrapeProfiles, scrapeInvestors, scrapePeople actions). One URL per line.", "items": { "type": "string" } }, "maxResults": { "title": "Max Results", "minimum": 0, "type": "integer", "description": "Maximum number of results to return. Use 0 for unlimited.", "default": 5 }, "includeFunding": { "title": "Include Funding Data", "type": "boolean", "description": "Scrape detailed funding rounds for each organization profile.", "default": true }, "includePeople": { "title": "Include People Data", "type": "boolean", "description": "Scrape founders and key executives for each organization profile.", "default": true }, "includeInvestors": { "title": "Include Investor Details", "type": "boolean", "description": "Scrape detailed investor information for each funding round.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Select proxies for the scraper. Residential proxies are strongly recommended for Crunchbase.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of pages to process in parallel. Lower values reduce chance of blocking.", "default": 3 }, "requestTimeout": { "title": "Request Timeout (seconds)", "minimum": 30, "maximum": 300, "type": "integer", "description": "Maximum time in seconds to wait for a page to load.", "default": 90 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Crunchbase Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: