{ "openapi": "3.0.1", "info": { "title": "Wellfound (AngelList) Jobs Scraper — Salary, Equity & Geo", "description": "Startup job listings from Wellfound (formerly AngelList Talent) with full descriptions, structured salary, geocoded locations, investor badges and the ATS each company hires through.", "version": "0.1", "x-build-id": "nVlDquG3tMYkXtBiM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/oswaldocarabano~wellfound-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-oswaldocarabano-wellfound-jobs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/oswaldocarabano~wellfound-jobs-scraper/runs": { "post": { "operationId": "runs-sync-oswaldocarabano-wellfound-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/oswaldocarabano~wellfound-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-oswaldocarabano-wellfound-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "roles": { "title": "Job roles", "type": "array", "description": "Role slugs to scrape, e.g. \"software-engineer\", \"product-manager\". Wellfound publishes 518 role slugs across 13 categories; leave empty to use the roles in `roleCategories` instead. Slugs come from wellfound.com/browse/tech-jobs.", "default": [], "items": { "type": "string" } }, "roleCategories": { "title": "Role categories", "type": "array", "description": "Scrape every role in these categories instead of naming roles one by one. Engineering alone holds 227 roles, so expect long runs.", "items": { "type": "string", "enum": [ "Engineering", "Product", "Design", "Data and Analytics", "Marketing", "Sales", "Operations", "Business and project management", "HR and recruiting", "Finance / Legal", "Content", "Other" ] }, "default": [] }, "locations": { "title": "Locations", "type": "array", "description": "Location slugs, e.g. \"san-francisco\", \"new-york\", \"london\". Wellfound publishes 306 location slugs. Each role is crossed with each location. Leave empty for no location filter.", "default": [], "items": { "type": "string" } }, "remoteOnly": { "title": "Remote jobs only", "type": "boolean", "description": "Only jobs Wellfound flags as remote. Note: Wellfound does not allow combining remote with a location filter, so this is ignored when `locations` is set.", "default": false }, "maxJobs": { "title": "Maximum jobs", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Hard cap on delivered job rows. There is no unlimited mode. One listing request returns about 28 unique jobs, and a role yields about 1,950 unique jobs on average.", "default": 500 }, "maxPagesPerRole": { "title": "Maximum pages per role", "minimum": 1, "maximum": 200, "type": "integer", "description": "Safety cap on pages per role. There is NO site-wide pagination limit: each role paginates until its corpus is exhausted and then redirects. Measured ceilings vary widely — engineer 130 pages, software-engineer 91, office-manager 37 — so a fixed value delivers a role's full corpus or a third of it depending on the role. Prefer capping with Maximum jobs.", "default": 40 }, "enrichFromJobPage": { "title": "Enrich from the job detail page", "type": "boolean", "description": "Fetch each job's own page to add structured salary (min/max/currency), latitude and longitude, benefits, the company website and its geocoded HQ. Costs one extra request per job. The full job description is already included without this.", "default": true }, "emitCompanies": { "title": "Also emit a companies dataset", "type": "boolean", "description": "Write a deduplicated `companies` dataset. A company with 56 jobs appears once.", "default": false }, "maxCacheAgeDays": { "title": "Maximum cache age (days)", "minimum": 0, "maximum": 30, "type": "integer", "description": "Serve cached rows up to this age. Set to 0 to force a fresh fetch. Every row reports `from_cache` and `data_age_hours` so you always know what you received.", "default": 1 }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 16, "type": "integer", "description": "Requests in flight per proxy session. Wellfound rate-limits per IP: 16 is the highest value measured without a block, and 24 triggers a 429 with a ~5 minute cooldown. Raising this does not make a run faster once you are rate-limited.", "default": 6 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Residential proxy strongly recommended. Measured: the same concurrency that returns 24 of 36 requests as HTTP 429 from a datacenter IP returns 48 of 48 as HTTP 200 from a residential IP.", "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 } } } } } } } } } }