{ "openapi": "3.0.1", "info": { "title": "Pracuj.pl Scraper · Poland Job Listings & Salaries", "description": "Scrape Pracuj.pl — Poland's #1 job board. Any search URL returns job title, company, salary, contract, work mode, location and an AI summary. Optional detail mode adds the full description, responsibilities, skills, tech stack and apply link. JSON or CSV.", "version": "0.0", "x-build-id": "YkvqbnZBJv2PJ63QQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~pracuj-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-pracuj-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~pracuj-scraper/runs": { "post": { "operationId": "runs-sync-memo23-pracuj-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~pracuj-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-pracuj-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Pracuj.pl search URLs", "type": "array", "description": "Full Pracuj.pl /praca/ search URLs. Each is paginated automatically (?pn=N) until `Maximum items` is reached.", "items": { "type": "string" } }, "flatten": { "title": "Flatten nested fields for CSV-friendly output", "type": "boolean", "description": "When enabled (default), nested objects/arrays (e.g. `locations`, `technologies`, `responsibilities`) are flattened into CSV-friendly columns. Disable to keep the full nested JSON.", "default": true }, "fetchDetails": { "title": "Fetch full job details (description, responsibilities, skills, technologies, apply link)", "type": "boolean", "description": "If enabled, opens each job's detail page to add the **full description**, **responsibilities**, **required & optional skills**, **technologies**, **job categories**, the **apply URL** and the **contact phone**. Adds one extra request per job and charges an `additional-data` event each time. Leave off for the fast/cheap search-only output.", "default": false }, "enrichEmails": { "title": "Enrich with employer contact emails (experimental, billed per email)", "type": "boolean", "description": "If enabled, tries to find a contact email for each employer by discovering the company's website (Clearbit) and reading its contact/about pages. Adds contactEmail + contactWebsite columns. Best-effort, billed per email found; never charged for misses.", "default": false }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on the number of jobs collected. Each search page returns ~50 jobs and paginates automatically; use this cap to control billing.", "default": 10000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of rows processed in parallel (mainly relevant when detail-fetch or employer-email enrichment is on). 6-12 is the sweet spot.", "default": 8 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Number of retries before a failed request is given up.", "default": 5 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Pracuj.pl blocks datacenter IPs (403), so **residential proxies are required**. Defaults to Apify Residential; the scraper retries on a block, rotating IP." } } }, "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 } } } } } } } } } }