{ "openapi": "3.0.1", "info": { "title": "Gupy.io – Public Jobs, Companies & Hiring Badges", "description": "Scrape public jobs from Gupy.io. Search by keyword, state, city, workplace type, job type, company, PWD, and feedback badge. Returns rich job, company, deadline, and badge fields.", "version": "1.0", "x-build-id": "fzyLgm2U5mOY7ekeI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~gupy-io-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-gupy-io-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~gupy-io-scraper/runs": { "post": { "operationId": "runs-sync-abotapi-gupy-io-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~gupy-io-scraper/run-sync": { "post": { "operationId": "run-sync-abotapi-gupy-io-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "search", "url" ], "type": "string", "description": "Search mode uses the filters below. URL mode accepts portal search URLs and Gupy company job URLs.", "default": "search" }, "searchTerm": { "title": "Search keyword", "type": "string", "description": "Job title, skill, or keyword. Leave empty to scrape all jobs matching the other filters.", "default": "" }, "state": { "title": "State", "enum": [ "", "Acre", "Alagoas", "Amapá", "Amazonas", "Bahia", "Ceará", "Distrito Federal", "Espírito Santo", "Goiás", "Maranhão", "Mato Grosso", "Mato Grosso do Sul", "Minas Gerais", "Pará", "Paraíba", "Paraná", "Pernambuco", "Piauí", "Rio de Janeiro", "Rio Grande do Norte", "Rio Grande do Sul", "Rondônia", "Roraima", "Santa Catarina", "São Paulo", "Sergipe", "Tocantins" ], "type": "string", "description": "Brazilian state filter. Leave empty for all states.", "default": "" }, "cities": { "title": "Cities", "type": "array", "description": "Exact Gupy city names. Leave empty for all cities.", "items": { "type": "string" }, "default": [] }, "workplaceTypes": { "title": "Workplace types", "type": "array", "description": "Remote, hybrid, or on-site jobs. Leave empty for all workplace types.", "items": { "type": "string", "enum": [ "remote", "hybrid", "on-site" ], "enumTitles": [ "Remote", "Hybrid", "On-site" ] }, "default": [] }, "jobTypes": { "title": "Job types", "type": "array", "description": "Gupy vacancy type values. Leave empty for all job types.", "items": { "type": "string", "enum": [ "vacancy_type_effective", "vacancy_type_apprentice", "vacancy_type_internship", "vacancy_legal_entity", "vacancy_type_trainee", "vacancy_type_temporary", "vacancy_type_freelancer", "vacancy_type_outsource", "vacancy_type_talent_pool", "vacancy_type_volunteer", "vacancy_type_parter", "vacancy_type_summer", "vacancy_type_intermittent" ], "enumTitles": [ "Full-time (Effective)", "Apprentice", "Internship", "Legal Entity", "Trainee", "Temporary", "Freelancer", "Outsourced", "Talent Pool", "Volunteer", "Partner", "Summer Job", "Intermittent" ] }, "default": [] }, "companies": { "title": "Companies", "type": "array", "description": "Exact Gupy career page names, for example '#sejaveriter' or 'PagBank'. Leave empty for all companies.", "items": { "type": "string" }, "default": [] }, "pwdOnly": { "title": "Only PWD-accessible jobs", "type": "boolean", "description": "Return only jobs marked for people with disabilities.", "default": false }, "friendlyBadgeOnly": { "title": "Only feedback-badge companies", "type": "boolean", "description": "Return only jobs from companies with Gupy feedback badge.", "default": false }, "urls": { "title": "URLs", "type": "array", "description": "Portal search URLs or Gupy company job URLs. Used only when Mode is URLs.", "items": { "type": "string" }, "default": [] }, "fetchDetails": { "title": "Fetch details", "type": "boolean", "description": "Fetch the full per-job record before saving each result. Applies to Search mode and to portal search URLs. Direct Gupy job URLs are always fetched in full, so this toggle does not affect them. Adds the detail-enrichment charge per enriched job that is actually saved — a job suppressed by Incremental mode (UNCHANGED, Emit unchanged off) is never charged even though its detail page was fetched. Also part of the Incremental mode baseline key: turning it on or off starts a separate tracked baseline.", "default": false }, "sortBy": { "title": "Sort order", "enum": [ "newest", "oldest", "company" ], "type": "string", "description": "Sort saved jobs after collection. Applies in both Search and URL mode.", "default": "newest" }, "maxItems": { "title": "Max items", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Maximum matching rows to save. Fewer rows may be returned when the selected source, keyword, and filters match fewer live records.", "default": 20 }, "maxPages": { "title": "Max pages", "minimum": 0, "type": "integer", "description": "Leave empty to walk every result page. Set 0 for unlimited; the run stops at Max items. A positive number caps the walk at that many pages.", "default": 0 }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 100, "type": "integer", "description": "API page size. Larger pages are faster; smaller pages are useful for debugging.", "default": 100 }, "resumeFromRunId": { "title": "Resume from a previous run (optional)", "type": "string", "description": "Paste a previous run ID or dataset ID to continue a full-catalogue walk across separate runs. Jobs already collected there (matched by job id) are skipped, so this run only saves the new ones. Leave empty for a normal fresh run. For recurring monitoring of the same search instead, use Incremental & dedup mode below." }, "incrementalMode": { "title": "Incremental & dedup mode", "type": "boolean", "description": "Remember this search's results between scheduled runs and classify each job as NEW, UPDATED, UNCHANGED, REAPPEARED, or EXPIRED (changeType field). Unlike Resume from a previous run (which continues one specific run by pasted id), this actor tracks its own baseline automatically, keyed by the search filters below (or State key). Off by default — every run scrapes and saves everything it finds.", "default": false }, "stateKey": { "title": "State key (optional)", "type": "string", "description": "Only used when Incremental & dedup mode is on. Leave empty to key the baseline automatically from the search filters (mode, keyword, state, cities, workplace/job types, companies, PWD/badge flags, URLs, Fetch details). Set your own text to track a named monitoring campaign explicitly, or to keep two schedules with identical filters from sharing one baseline." }, "emitUnchanged": { "title": "Emit unchanged records", "type": "boolean", "description": "Only used when Incremental & dedup mode is on. When off (default), a job identical to the last tracked run is skipped — not saved, not billed. When on, UNCHANGED rows are saved (and billed) too, alongside NEW/UPDATED/REAPPEARED ones.", "default": false }, "emitExpired": { "title": "Emit expired records", "type": "boolean", "description": "Only used when Incremental & dedup mode is on. When on, a job tracked by a previous run but no longer found after a complete scan of this search is saved once with changeType EXPIRED (and billed as a normal result row). Only fires on a run that reached the natural end of the walk — Max items/Max pages capping the run, or Resume from a previous run being set, skips EXPIRED detection for that run and keeps the previous state as-is.", "default": false }, "mcpConnectors": { "title": "Pipe results into your apps (optional)", "type": "array", "description": "Optionally send the scraped jobs into the apps you already use, via Model Context Protocol (MCP) connectors. Authorize a connector once under Apify → Settings → Integrations, then select it here. The connector receives a condensed, human-readable summary per job (title + key fields), not the full JSON; the complete record stays in the dataset. Leave empty to skip. Supported: Notion (https://mcp.notion.com/mcp), Linear (https://mcp.linear.app/sse), Airtable (https://mcp.airtable.com/mcp), Apify (https://mcp.apify.com)." }, "notionParentPageUrl": { "title": "Notion parent page (Notion connector only)", "type": "string", "description": "URL (or id) of the Notion page under which job pages are created. Required to enable the Notion export; ignored by other connectors." }, "maxNotifyListings": { "title": "Max jobs to export per connector", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap on jobs written to each connector per run. Does not affect the dataset.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Works on every plan, including Free. Apify Proxy is recommended for reliability and is the default; if you see repeated source errors, enable it.", "default": { "useApifyProxy": true, "apifyProxyGroups": [] } } } }, "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 } } } } } } } } } }