{ "openapi": "3.0.1", "info": { "title": "Crunchbase Companies Scraper", "description": "Crunchbase Companies Scraper SD - Crunchbase Companies Scraper is a company data tool that extracts Crunchbase companies from Crunchbase News funding coverage: name, Crunchbase URL, amount raised, round type, article and date, filtered by keyword, category, date and minimum amount.", "version": "1.0", "x-build-id": "vKlZEmWad1kUK6xLd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neuro-scraper~crunchbase-companies-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neuro-scraper-crunchbase-companies-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neuro-scraper~crunchbase-companies-scraper/runs": { "post": { "operationId": "runs-sync-neuro-scraper-crunchbase-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neuro-scraper~crunchbase-companies-scraper/run-sync": { "post": { "operationId": "run-sync-neuro-scraper-crunchbase-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "newsCategory": { "title": "Crunchbase News category", "type": "string", "description": "Find companies in this Crunchbase News category, by name: Venture, Seed funding, Artificial intelligence, Fintech, M&A, IPO, Cybersecurity ... The category id is looked up on every run. Each company linked in a matching article becomes a row." }, "newsQuery": { "title": "Crunchbase News keyword", "type": "string", "description": "Find companies in Crunchbase News articles that match this keyword, e.g. \"series a\", \"fintech\" or \"robotics\" (WordPress search: a loose word match)." }, "announcedAfter": { "title": "Announced on or after", "type": "string", "description": "Only articles published on or after this day, e.g. 2026-09-01 (YYYY-MM-DD)." }, "announcedBefore": { "title": "Announced on or before", "type": "string", "description": "Only articles published on or before this day, e.g. 2026-10-01 (YYYY-MM-DD)." }, "minAmountUsd": { "title": "Minimum amount raised (USD)", "minimum": 0, "type": "integer", "description": "Only companies with a dollar amount of at least this much in the same sentence of the article, e.g. 10000000 for rounds of $10M and up. Investors named in that sentence (\"led by ...\") match too." }, "maxAmountUsd": { "title": "Maximum amount raised (USD)", "minimum": 0, "type": "integer", "description": "Only companies with a dollar amount of at most this much in the same sentence of the article, e.g. 5000000 for rounds up to $5M." }, "roundTypes": { "title": "Round types", "type": "array", "description": "Only companies whose sentence names one of these: Pre-Seed, Seed, Angel, Series A ... Series K, Venture, Venture Debt, Debt, Growth Equity, Private Equity, Convertible Note, Grant, IPO, SPAC, Acquisition. Matched in the article text (applied here, not by Crunchbase).", "items": { "type": "string" } }, "skipInvestors": { "title": "Skip investors", "type": "boolean", "description": "Leave out organizations the sentence names as backers (\"led by ...\", \"... participated\"), so the list holds the funded companies. The role is guessed from the article wording and shown in mentionRole.", "default": false }, "maxItems": { "title": "Max companies", "minimum": 1, "maximum": 100000, "type": "integer", "description": "How many company rows to return. The Actor reads Crunchbase News page after page (20 articles each) until this many companies are found or the archive ends.", "default": 20 }, "startUrls": { "title": "Crunchbase company URLs (profile pages)", "type": "array", "description": "Crunchbase organization pages to open in a headless browser, e.g. https://www.crunchbase.com/organization/airbnb or the permalink airbnb. Measured 2026-10-09: Crunchbase answered our only test (US residential IP) with a Cloudflare block page, so expect these to fail; a failed profile is logged and not charged.", "items": { "type": "string" } }, "fetchProfiles": { "title": "Also try each company's Crunchbase profile", "type": "boolean", "description": "Off (default): fast news rows. On: opens every found company's profile page in a headless browser; when Cloudflare blocks it (measured 2026-10-09) the row keeps its news fields with profileStatus \"blocked\", and after 3 blocks in a row no more profiles are tried.", "default": false }, "rawMode": { "title": "Include raw Crunchbase cards", "type": "boolean", "description": "Profile mode only: adds `rawCards` (every property and card the profile page delivers) to each row and saves the page HTML in the key-value store as PAGE-.html.", "default": false }, "maxSessions": { "title": "Browser sessions per profile", "minimum": 1, "maximum": 3, "type": "integer", "description": "Profile mode only: on a Cloudflare block or check the Actor tries a new browser session (new proxy IP) up to this many times. It never answers a CAPTCHA.", "default": 3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential proxy in the United States is the default. Crunchbase News needs no special proxy; profile pages are behind Cloudflare.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }