{
"openapi": "3.0.1",
"info": {
"title": "🚀 Y Combinator Scraper",
"description": "Y Combinator Scraper extracts startup profiles, founders, industries, batches, locations, websites, and company details from Y Combinator. Ideal for startup research, lead generation, competitor analysis, and market intelligence.",
"version": "1.0",
"x-build-id": "mrpttvgnEVwQSc80y"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/scraper-engine~y-combinator-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-scraper-engine-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/scraper-engine~y-combinator-scraper/runs": {
"post": {
"operationId": "runs-sync-scraper-engine-y-combinator-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/scraper-engine~y-combinator-scraper/run-sync": {
"post": {
"operationId": "run-sync-scraper-engine-y-combinator-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"required": [
"urls"
],
"properties": {
"urls": {
"title": "🔍 YC Companies Search URL(s)",
"type": "array",
"description": "🌐 One or more Y Combinator directory search URLs (bulk supported). Go to the YC directory, apply the filters you want (batch, industry, region, stage, tags, hiring status, ...), copy the full URL from the address bar, and paste it here — one per line, or upload a file. Every result across all pasted URLs is merged and de-duplicated.",
"items": {
"type": "string"
}
},
"scrapeFounders": {
"title": "👥 Scrape Founders",
"type": "boolean",
"description": "✨ When enabled, each company record includes its founders — name, title, bio, LinkedIn, X (Twitter), and email availability.",
"default": true
},
"scrapeOpenJobs": {
"title": "💼 Scrape Open Jobs",
"type": "boolean",
"description": "📌 When enabled, each company record includes its full open-job listings — title, description, location, salary, equity, skills, and more. Leave off for faster runs if you only need the job count.",
"default": false
},
"maxCompanies": {
"title": "🎯 Maximum Companies",
"minimum": 1,
"type": "integer",
"description": "✂️ Stop after this many companies (across all search URLs combined). Leave empty for no limit.",
"default": 10
},
"scrapeAllCompanies": {
"title": "🌍 Scrape ALL Companies",
"type": "boolean",
"description": "🗂️ Set to true to scrape every company in the YC directory (5,500+, all batches). When enabled, the 🔍 Search URL(s) and 🎯 Maximum Companies fields above are ignored entirely.",
"default": false
},
"proxyConfiguration": {
"title": "🛡️ Proxy Configuration",
"type": "object",
"description": "🌐 By default the Actor connects to Y Combinator with NO proxy for maximum speed. If a request is rejected or blocked, it automatically escalates: ⚡ No proxy → 🏢 Datacenter proxy → 🏠 Residential proxy (retried up to 3×) — then sticks with Residential for every remaining request in the run. Every escalation is logged clearly. You can also force a specific tier yourself here."
},
"maxConcurrency": {
"title": "⚡ Max Concurrency",
"minimum": 1,
"maximum": 20,
"type": "integer",
"description": "🚦 How many companies to enrich in parallel. Higher is faster but more likely to trigger rate limiting (which the proxy ladder above will then handle automatically).",
"default": 5
},
"requestDelay": {
"title": "⏱️ Delay Between Requests (seconds)",
"minimum": 0,
"maximum": 10,
"type": "number",
"description": "🐢 Optional polite delay before each request, in seconds. Float values are supported (e.g. 0.5). Helps avoid rate limiting on very large runs.",
"default": 0
},
"maxRetries": {
"title": "🔁 Max Retries per Request",
"minimum": 1,
"maximum": 5,
"type": "integer",
"description": "🔄 How many times to retry a single request on a network error or server hiccup (5xx) before giving up on that attempt. Separate from the proxy escalation ladder above.",
"default": 3
}
}
},
"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
}
}
}
}
}
}
}
}
}
}