{ "openapi": "3.0.1", "info": { "title": "Seafarer Jobs Scraper — 4 Sources, 19K+ Listings", "description": "Seafarer and maritime crewing vacancies from four boards (Martide, Crewell, FindSeaJobs, SeaCrew) in one normalised dataset, ~19,000 listings. Adds monthly-USD salary, rank tier, joining-date countdown and a dataCompleteness flag. Pick boards with sourcesToInclude. Each run writes an HTML dashboard.", "version": "0.1", "x-build-id": "yS4BQ1plloye4Gnzu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solalab_digital~maritime-crewing-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solalab_digital-maritime-crewing-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solalab_digital~maritime-crewing-jobs-scraper/runs": { "post": { "operationId": "runs-sync-solalab_digital-maritime-crewing-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solalab_digital~maritime-crewing-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-solalab_digital-maritime-crewing-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sourcesToInclude": { "title": "Source sites to scrape", "uniqueItems": true, "type": "array", "description": "Which job boards to crawl. All four are included by default, which is roughly 19,000 live vacancies in total. Deselect sources you do not need: every source you include multiplies the number of records — and therefore the cost — of a full run. Rough sizes: Martide ~130, Crewell ~3,600, FindSeaJobs ~7,300, SeaCrew ~8,500.", "items": { "type": "string", "enum": [ "martide", "crewell", "findseajobs", "seacrew" ], "enumTitles": [ "Martide (martide.com) — full detail pages", "Crewell (crewell.net) — listing cards only, see docs", "FindSeaJobs (findseajobs.com) — full detail pages, may need a proxy", "SeaCrew (seacrew.net) — full detail pages" ] }, "default": [ "martide", "crewell", "findseajobs", "seacrew" ] }, "maxItems": { "title": "Maximum jobs to scrape", "minimum": 0, "type": "integer", "description": "Stop the whole run after this many job records have been saved across all sources combined. Set to 0 to scrape every job currently listed (~19,000 across all four boards — a full run takes well over Apify's 5-minute automatic health-check window, so leave this capped unless you specifically want the full pull). Useful for capping cost on a paid run, for a quick sample before a full crawl, or for picking a specific size like 1,000/2,000/10,000.", "default": 60 }, "maxPages": { "title": "Maximum listing pages per source", "minimum": 0, "type": "integer", "description": "Limit how many listing pages are visited on each included source. Set to 0 for no limit, in which case the Actor keeps following pagination until a page returns no job cards. This limit is per source, not shared: with 4 sources and maxPages=5, up to 20 listing pages are visited in total. Jobs per page: Martide ~50, Crewell 20, FindSeaJobs 20, SeaCrew 30.", "default": 0 }, "startPage": { "title": "Start from listing page", "minimum": 1, "type": "integer", "description": "The 1-based listing page each source begins from. Leave at 1 for a normal run; raise it only to resume or to split a large crawl across several runs. Applied to every included source alike.", "default": 1 }, "includeJobDescription": { "title": "Include job description text", "type": "boolean", "description": "Include the free-text job description and its original HTML in each record. Turn this off for a smaller, tabular dataset that is easier to load into a spreadsheet or CRM.", "default": true }, "maxRequestsPerMinute": { "title": "Maximum requests per minute, per source", "minimum": 1, "maximum": 240, "type": "integer", "description": "Courtesy rate limit applied to each source separately. Each site's own published limit still wins where it is stricter: Crewell declares a 10-second crawl-delay in its robots.txt and is never crawled faster than 6 requests per minute regardless of this setting. Lower this if you run the Actor frequently.", "default": 60 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Usually not needed. Martide, Crewell and SeaCrew serve plain server-rendered HTML with no bot protection. FindSeaJobs sits behind a CDN that rejects some datacentre IP ranges; on Apify's platform it normally works with no proxy, but if it returns no records, re-run with a RESIDENTIAL proxy group. A blocked source never fails the run — the other three complete normally.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }