{ "openapi": "3.0.1", "info": { "title": "Y Combinator Scraper", "description": "Turn Y Combinator's public directory into investor-grade data. Extract company profiles, founders, open roles, press, and Launch YC postsβ€”filter by batch or scrape the full catalog. Built for lead gen, recruiting, and deal sourcing. Export ready: JSON, CSV, Excel.", "version": "0.1", "x-build-id": "wiEOBxJiBU9HBjO8N" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/insights_data~y-combinator-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-insights_data-y-combinator-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/insights_data~y-combinator-scraper/runs": { "post": { "operationId": "runs-sync-insights_data-y-combinator-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/insights_data~y-combinator-scraper/run-sync": { "post": { "operationId": "run-sync-insights_data-y-combinator-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "πŸ” YC Directory URLs", "type": "array", "description": "One or more Y Combinator URLs to scrape. Two kinds are supported, and you can mix both in the same list:\n\n- πŸ—‚οΈ **A directory search URL**, e.g. `https://www.ycombinator.com/companies?batch=Summer%202026` β€” go to the [YC directory](https://www.ycombinator.com/companies), apply filters, copy the address bar URL, paste it here.\n- 🏒 **A single company's profile URL**, e.g. `https://www.ycombinator.com/companies/airbnb` β€” scrapes just that company.\n\n⚠️ Not required if πŸš€ **Scrape All Companies** below is turned on.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxCompanies": { "title": "πŸ’― Maximum Companies", "minimum": 1, "type": "integer", "description": "Stop after collecting this many companies. Increase this for larger runs, or turn on πŸš€ Scrape All Companies for the full directory.", "default": 10 }, "scrapeFounders": { "title": "πŸ§‘β€πŸ’Ό Scrape Founders", "type": "boolean", "description": "Include each company's founders β€” name, title, bio, email availability, LinkedIn and X (Twitter).", "default": true }, "scrapeOpenJobs": { "title": "πŸ’Ό Scrape Open Jobs", "type": "boolean", "description": "Include full open-job details β€” title, description, location, salary, equity, skills, visa. Off by default because it fetches one extra page per job.", "default": false }, "scrapeNews": { "title": "πŸ“° Scrape News & Press Mentions", "type": "boolean", "description": "Include press/media mentions found on the company's profile β€” free to collect, no extra requests.", "default": true }, "scrapeLaunchPosts": { "title": "πŸŽ‰ Scrape Launch YC Posts", "type": "boolean", "description": "Include the company's Launch YC posts (title, tagline, URL, date, upvotes) β€” free to collect, no extra requests.", "default": true }, "includeLaunchBody": { "title": "πŸ“ Include Full Launch Post Text", "type": "boolean", "description": "Also include the full text of each Launch YC post. Off by default since it can be long. Only applies when πŸŽ‰ Scrape Launch YC Posts is on.", "default": false }, "sortByLaunchDate": { "title": "πŸ•’ Sort by Launch Date (Newest First)", "type": "boolean", "description": "Order results by launch date instead of relevance.", "default": false }, "launchedAfter": { "title": "πŸ“… Launched After", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$", "type": "string", "description": "Only include companies launched on or after this date." }, "launchedBefore": { "title": "πŸ“… Launched Before", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$", "type": "string", "description": "Only include companies launched on or before this date." }, "scrapeAllCompanies": { "title": "Scrape All Companies", "type": "boolean", "description": "Scrape every company in the directory, ignoring πŸ” YC Directory URLs and πŸ’― Maximum Companies above. This can take a long time and produce a very large dataset.", "default": false }, "teamSizeMin": { "title": "πŸ‘₯ Minimum Team Size", "minimum": 0, "type": "integer", "description": "Only include companies with at least this many team members." }, "teamSizeMax": { "title": "πŸ‘₯ Maximum Team Size", "minimum": 0, "type": "integer", "description": "Only include companies with at most this many team members." }, "proxyConfiguration": { "title": "🌐 Proxy Configuration", "type": "object", "description": "Apify Proxy powers the 🟑 Datacenter and πŸ”΄ Residential fallback tiers. Requests still start 🟒 Direct (no proxy) for maximum speed β€” proxies only kick in automatically if Y Combinator blocks a request.", "default": { "useApifyProxy": true } }, "concurrency": { "title": "⚑ Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many companies to scrape in parallel.", "default": 5 }, "maxRetries": { "title": "πŸ” Max Retries", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many times to retry a blocked or failed request on the Residential proxy tier before giving up on it.", "default": 3 }, "requestDelay": { "title": "⏱️ Delay Between Requests (seconds)", "minimum": 0, "maximum": 10, "type": "number", "description": "Polite random delay added between requests to reduce the chance of being blocked. 0 = as fast as possible.", "default": 0 } } }, "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 } } } } } } } } } }