{ "openapi": "3.0.1", "info": { "title": "AI/ML Jobs Scraper", "description": "Scrape AI/ML jobs from 150+ companies via Greenhouse, Lever, RemoteOK, WeWorkRemotely, and YC. Extracts skills, frameworks, salary, and experience. Optional AI enrichment. Change detection and webhook alerts.", "version": "0.0", "x-build-id": "v3jxB98h5dZZTCi1B" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lissome_dancer~ai-ml-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lissome_dancer-ai-ml-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lissome_dancer~ai-ml-jobs-scraper/runs": { "post": { "operationId": "runs-sync-lissome_dancer-ai-ml-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lissome_dancer~ai-ml-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-lissome_dancer-ai-ml-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sources": { "title": "Job sources", "type": "array", "description": "Which job boards to scrape. All five are enabled by default.", "default": [ "greenhouse", "lever", "remoteok", "weworkremotely", "yc" ], "items": { "type": "string" } }, "keywords": { "title": "Keyword filter", "type": "array", "description": "Only include jobs containing at least one of these keywords. Leave empty to include all AI-relevant jobs.", "default": [], "items": { "type": "string" } }, "companies": { "title": "Company filter", "type": "array", "description": "Only include jobs from these companies (partial match). Leave empty to include all companies.", "default": [], "items": { "type": "string" } }, "parseAllResults": { "title": "Parse all results", "type": "boolean", "description": "Ignore the max output limit and scrape all available jobs from the selected sources.", "default": false }, "maxItems": { "title": "Max output items", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum number of job records to output per run. Ignored if 'Parse all results' is enabled.", "default": 1000 }, "classifyWithAI": { "title": "Enable AI enrichment", "type": "boolean", "description": "Use an LLM to enrich jobs with structured metadata (skills, frameworks, experience level). Requires GROQ_API_KEY or OPENROUTER_API_KEY.", "default": false }, "classificationMode": { "title": "Classification mode", "enum": [ "deterministic", "hybrid", "ai" ], "type": "string", "description": "How to classify jobs. Deterministic is free and fast. Hybrid uses LLM only for uncertain jobs. AI classifies every job with LLM.", "default": "hybrid" }, "llmProvider": { "title": "LLM provider", "enum": [ "groq", "openrouter" ], "type": "string", "description": "Which LLM to use for AI enrichment. Set the corresponding API key in environment variables.", "default": "groq" }, "tier": { "title": "Access tier", "enum": [ "free", "starter", "pro", "enterprise" ], "type": "string", "description": "Controls output limits and features. Free tier includes 100 jobs from 2 sources.", "default": "starter" }, "detectChanges": { "title": "Detect changes (incremental mode)", "type": "boolean", "description": "Compare this run against the previous run to detect new, updated, and removed jobs.", "default": true }, "proxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Route requests through Apify Proxy to avoid rate limits. Recommended for large runs.", "default": false }, "customGreenhouseTokens": { "title": "Custom Greenhouse tokens", "type": "array", "description": "Add custom Greenhouse company board tokens. Find tokens at boards.greenhouse.io/{token}.", "default": [], "items": { "type": "string" } }, "customLeverSlugs": { "title": "Custom Lever slugs", "type": "array", "description": "Add custom Lever company slugs. Find slugs at lever.co/{slug}.", "default": [], "items": { "type": "string" } }, "alertKeywords": { "title": "Alert keywords", "type": "array", "description": "Send webhook when a new job matches these keywords. Requires webhook URL.", "default": [], "items": { "type": "string" } }, "alertMinSalary": { "title": "Alert minimum salary", "minimum": 0, "type": "integer", "description": "Send webhook when a new job has salary above this threshold. Set to 0 to disable.", "default": 0 }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Slack, Discord, or custom webhook URL for job alerts. Leave empty to disable.", "default": "" } } }, "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 } } } } } } } } } }