{ "openapi": "3.0.1", "info": { "title": "Y Combinator Companies Scraper", "description": "Scrapes the Y Combinator startup directory by industry. Each row carries company name, description, YC batch, location, logo and social links, with optional founders, team size, tags and open job postings.", "version": "0.1", "x-build-id": "yBdDdRVH2bPFTyQPx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~ycombinator-companies-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-ycombinator-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~ycombinator-companies-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-ycombinator-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~ycombinator-companies-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-ycombinator-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "industry": { "title": "Industry", "type": "string", "description": "One YC industry category slug, e.g. `developer-tools`, `fintech`, `generative-ai`, `machine-learning`, `healthcare`. There are 107 in total — the Actor reads the current, authoritative list from Y Combinator's own sitemap on every run, so it never goes stale, and refuses an unrecognised slug up front with the real list rather than silently returning nothing.\n\nFor several industries in one run, use `industries` below instead.", "default": "" }, "industries": { "title": "Multiple industries (advanced)", "type": "array", "description": "Optional. Run several industries in one Actor call, each producing its own SEARCH_SUMMARY row. When set, the `industry` field above is ignored.", "default": [], "items": { "type": "string" } }, "includeCompanyDetails": { "title": "Fetch full company details", "type": "boolean", "description": "The company list already carries name, one-liner description, location, YC batch, logo and social links. This fetches each company's own page for founders (names, roles, LinkedIn), team size, year founded, tags, and open job postings — one extra request per company.", "default": false }, "maxItems": { "title": "Max companies per industry", "minimum": 0, "type": "integer", "description": "Stop after this many companies per industry. Set to 0 for everything in that industry.", "default": 200 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 12, "type": "integer", "description": "Upper bound on requests in flight at once, across all industries and detail fetches.", "default": 4 }, "minRequestInterval": { "title": "Minimum seconds between requests", "minimum": 0, "maximum": 30, "type": "integer", "description": "Paces how often requests START, without tying up a concurrency slot. No rate limiting was observed, so this defaults to 0.", "default": 0 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential by default. No bot challenge appeared on any of the 7 TLS fingerprints tested across list and detail pages, but datacentre egress from a cloud platform can be fingerprinted differently from a local test.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }