{ "openapi": "3.0.1", "info": { "title": "Wellfound Jobs + Startup Intelligence Scraper", "description": "Scrape wellfound.com startup jobs with company intelligence: funding stage, founders, and investor data. Free-text search plus company-only lead-gen mode and real-time Slack/Telegram alerts on new postings.", "version": "0.1", "x-build-id": "KbSNb0elU5gQADmXE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blackfalcondata~wellfound-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blackfalcondata-wellfound-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blackfalcondata~wellfound-scraper/runs": { "post": { "operationId": "runs-sync-blackfalcondata-wellfound-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blackfalcondata~wellfound-scraper/run-sync": { "post": { "operationId": "run-sync-blackfalcondata-wellfound-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "🔍 Search Query (free-text)", "type": "string", "description": "Free-text job search (e.g. \"rust engineer\", \"ML ops\", \"solidity developer\"). Maps to Wellfound's /jobs?q= endpoint. Combine with roles/searchUrls to union multiple searches." }, "roles": { "title": "📁 Role Categories", "uniqueItems": true, "type": "array", "description": "Wellfound's built-in role categories. Each spawns a separate search thread. Common slugs: software-engineer, product-manager, product-designer, data-analyst, growth-marketer, sales-manager, account-manager, hr-manager, operations-manager, financial-analyst, graphic-designer, ui-ux-designer. Free-text — you can also try other slugs.", "items": { "type": "string" } }, "searchUrls": { "title": "🔗 Search URLs (paste Wellfound URLs)", "uniqueItems": true, "type": "array", "description": "Paste full Wellfound search URLs (e.g. https://wellfound.com/role/l/product-manager/berlin). Each URL spawns a separate search thread. Mix with query/roles freely — all deduplicate by job ID.", "items": { "type": "string" } }, "location": { "title": "📍 Locations", "uniqueItems": true, "type": "array", "description": "One or more location slugs (e.g. [\"new-york\", \"san-francisco\", \"berlin\"]). Each location × role combination spawns a separate search thread. For /jobs?q= searches, use a human-readable city name. Ignored for pasted searchUrls (they carry their own location).", "items": { "type": "string" } }, "excludeLocations": { "title": "🚫 Exclude Locations", "uniqueItems": true, "type": "array", "description": "Drop jobs whose locationNames match any of these (substring match, e.g. \"India\" drops \"Bangalore, India\"). Applied after fetch.", "items": { "type": "string" } }, "remote": { "title": "🏠 Remote Only", "type": "boolean", "description": "When true, scrapes remote-filtered URLs. Ignored for pasted searchUrls.", "default": false }, "originLocation": { "title": "🎯 Origin Location (for radius filter)", "type": "string", "description": "City name for radius-based filtering (e.g. \"San Francisco\", \"New York\"). Used with radiusMiles or radiusKm. Supports ~35 major US + international startup hubs — unsupported cities skip the radius filter with a warning." }, "radiusMiles": { "title": "📏 Radius (miles)", "minimum": 0, "maximum": 500, "type": "integer", "description": "Drop jobs further than N miles from originLocation. Requires enrichDetail=true (needs job coordinates). US-standard unit.", "default": 0 }, "radiusKm": { "title": "📏 Radius (km, alt)", "minimum": 0, "maximum": 800, "type": "integer", "description": "Kilometer alternative to radiusMiles. If both set, radiusMiles wins. Use this for EU-based searches.", "default": 0 }, "jobType": { "title": "💼 Job Type", "enum": [ "fulltime", "parttime", "contract", "internship" ], "type": "string", "description": "Filter by employment type. Matches Wellfound's jobType field (substring, case-insensitive)." }, "experienceLevel": { "title": "🎓 Experience Level", "enum": [ "entry", "mid", "senior", "staff" ], "type": "string", "description": "Filter by minimum required years of experience. Entry: 0-2, Mid: 2-5, Senior: 5-8, Staff+: 8+. Jobs without experience data are kept." }, "salaryMin": { "title": "💰 Minimum Salary (USD)", "minimum": 0, "type": "integer", "description": "Drop jobs whose salary max is below this. 0 = no minimum. Jobs without salary data are dropped when minimum is set.", "default": 0 }, "salaryMax": { "title": "💰 Maximum Salary (USD)", "minimum": 0, "type": "integer", "description": "Drop jobs whose salary min exceeds this. 0 = no maximum.", "default": 0 }, "equityMin": { "title": "📈 Minimum Equity (%)", "minimum": 0, "maximum": 100, "type": "number", "description": "Drop jobs whose max equity grant is below this percent. 0 = no minimum. Jobs without equity data are dropped when minimum is set.", "default": 0 }, "visaSponsorship": { "title": "🛂 Visa Sponsorship", "type": "boolean", "description": "Filter by visa sponsorship stance detected from job description heuristics. true = only jobs that explicitly offer sponsorship; false = drop jobs that explicitly refuse sponsorship. Unset = no filter. Detection is conservative — jobs without clear phrasing pass when true is not required." }, "includeKeywords": { "title": "📝 Include Keywords", "type": "object", "description": "Require at least one of these keywords. Example: {\"keywords\":[\"rust\",\"golang\"],\"matchTitle\":true,\"matchDescription\":true,\"matchSkills\":true}. Matches default to all three fields." }, "excludeKeywords": { "title": "🚫 Exclude Keywords", "type": "object", "description": "Drop jobs containing any of these keywords. Same shape as includeKeywords." }, "fromDate": { "title": "📅 From Date", "type": "string", "description": "Only include jobs posted on or after this date. Accepts YYYY-MM-DD or ISO-8601." }, "toDate": { "title": "📅 To Date", "type": "string", "description": "Only include jobs posted on or before this date. Accepts YYYY-MM-DD or ISO-8601." }, "maxAgeMinutes": { "title": "⏰ Max Age (minutes)", "minimum": 0, "type": "integer", "description": "Only include jobs posted within the last N minutes. 0 = no limit. Pairs well with scheduled runs for real-time monitoring.", "default": 0 }, "customFilters": { "title": "🔧 Custom Filters (advanced)", "type": "array", "description": "Array of rules applied to any output field. Each rule: {\"field\":\"\",\"op\":\"includes|notIncludes|equals|notEquals|gt|gte|lt|lte\",\"value\":...}. Example: [{\"field\":\"companyFundingStage\",\"op\":\"equals\",\"value\":\"series-b\"}, {\"field\":\"description\",\"op\":\"notIncludes\",\"value\":\"wordpress\"}]." }, "maxResults": { "title": "💯 Max Results", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Maximum total job listings to return across all search threads (0 = unlimited).", "default": 100 }, "maxPages": { "title": "📄 Max Pages per Search", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum SERP pages per search thread (each page has ~42 jobs).", "default": 10 }, "enrichDetail": { "title": "📄 Enrich from Detail Pages (recommend sessionCookie)", "type": "boolean", "description": "Fetch each job detail page for structured salary (min/max/currency/period), company website, industry, benefits, geolocation, skills, and visa-sponsorship detection. Wellfound's detail pages are DataDome-protected for unauthenticated residential-proxy IPs, so when enabled WITHOUT sessionCookie most detail fetches will 403 and those fields stay null. Provide sessionCookie (see below) to unlock reliable enrichment.", "default": false }, "enrichCompany": { "title": "🏢 Enrich Company Profiles (requires sessionCookie)", "type": "boolean", "description": "Fetch /company/{slug} for each unique company to extract funding stage, total raised, investors, founders (with LinkedIn), social links, full description, founded year, and markets. REQUIRES sessionCookie — Wellfound's /company/ pages are DataDome-protected for unauthenticated requests. Without a cookie, SERP-level fields (name, logo, slug, size) still populate; deep fields stay null.", "default": false }, "sessionCookie": { "title": "🔐 Wellfound Session Cookie (for company enrichment)", "type": "string", "description": "Your logged-in Wellfound session cookie. How to get it: (1) log in to wellfound.com (free account works), (2) open DevTools → Application → Cookies → wellfound.com, (3) copy the value of '_wellfound_session' — or paste the entire Cookie header string with all name=value pairs separated by '; '. Treat as a password. Typically lives 2-4 weeks. Only used when enrichCompany=true." }, "companyOnlyMode": { "title": "🎯 Company-Only Output (lead-gen mode)", "type": "boolean", "description": "Emit ONE record per unique company instead of one per job, with aggregated jobCount and sample job titles. Ideal for lead-gen / recruiter / sourcer workflows. Incremental mode does not apply (aggregation is per-run). Pairs well with enrichCompany for rich contact data.", "default": false }, "descriptionMaxLength": { "title": "✂️ Description Max Length", "minimum": 0, "type": "integer", "description": "Truncate job description to this many characters. 0 = no truncation.", "default": 0 }, "compact": { "title": "📦 Compact Output", "type": "boolean", "description": "Output only core fields (id, title, companyName, portalUrl, locationNames, remote, compensation, postedAt). For AI-agent/MCP workflows.", "default": false }, "incrementalMode": { "title": "♻️ Incremental Mode", "type": "boolean", "description": "Compare against previous run state. Only emits NEW and UPDATED jobs. Requires stateKey.", "default": false }, "stateKey": { "title": "🔑 State Key", "type": "string", "description": "Stable identifier for the tracked search universe (e.g. 'us-software-remote'). Required when incrementalMode is true. IMPORTANT: changing your filters (roles, searchUrls, location) will cause jobs outside the new universe to be marked EXPIRED. Use a NEW stateKey if you change search scope." }, "emitUnchanged": { "title": "♻️ Emit Unchanged Records", "type": "boolean", "description": "When incremental, also emit records that have not changed since last run.", "default": false }, "emitExpired": { "title": "⚰️ Emit Expired Records", "type": "boolean", "description": "When incremental, also emit records no longer found (job removed or expired).", "default": false }, "skipReposts": { "title": "🚫 Skip Reposts", "type": "boolean", "description": "When enabled, suppress jobs that appear to be reposts of previously seen (and now expired) jobs based on content-hash matching.", "default": false }, "telegramToken": { "title": "📱 Telegram Bot Token", "type": "string", "description": "Telegram bot token from @BotFather. Sends notifications when new jobs are emitted. Pairs well with incrementalMode for real-time alerts." }, "telegramChatId": { "title": "💬 Telegram Chat / Channel ID", "type": "string", "description": "Chat ID (from @userinfobot) or channel ID (starts with -100 for channels). Required when telegramToken is set." }, "slackWebhookUrl": { "title": "💼 Slack Incoming Webhook URL", "type": "string", "description": "Slack incoming webhook URL (Slack App → Incoming Webhooks → Add New Webhook). Formats jobs as Slack blocks with company, salary, funding stage, and location." }, "discordWebhookUrl": { "title": "💬 Discord Webhook URL", "type": "string", "description": "Discord channel webhook URL (Server Settings → Integrations → Webhooks → New Webhook). Sends rich embeds colour-coded by change type (green=NEW, amber=UPDATED)." }, "notificationLimit": { "title": "🔢 Notification Limit", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of jobs to send per notification batch. Prevents spam on large result sets.", "default": 5 }, "includeRunMetadata": { "title": "📣 Include Run Summary in Notifications", "type": "boolean", "description": "Prepend a one-line summary (search label + total count) to each notification batch.", "default": true }, "notifyOnlyChanges": { "title": "🆕 Notify Only on Changes", "type": "boolean", "description": "When ON (default) AND incrementalMode is ON, send notifications only for NEW and UPDATED jobs. Without incrementalMode, this has no effect (all emitted jobs are notified).", "default": true }, "proxyConfiguration": { "title": "🛡️ Proxy Configuration", "type": "object", "description": "Proxy configuration. Strongly recommended for reliable delivery." } } }, "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 } } } } } } } } } }