{ "openapi": "3.0.1", "info": { "title": "Community First Yorkshire Jobs Scraper", "description": "Scrape jobs and other portfolio content from communityfirstyorkshire.org.uk via WP-JSON portfolio CPT. Filter by taxonomy (default jobs ≈ 6 vacancies). Title, full HTML, location, apply email/URL, best-effort closing date + salary regex. JSON or CSV out.", "version": "0.0", "x-build-id": "YqmlDoVkKNceQOQBV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~cfy-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-cfy-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~cfy-scraper/runs": { "post": { "operationId": "runs-sync-memo23-cfy-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~cfy-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-cfy-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "communityfirstyorkshire.org.uk URLs", "type": "array", "description": "Supported shapes: `/portfolio-item//`, `/wp-json/wp/v2/portfolio`, `/wp-json/wp/v2/portfolio/`. Leave empty + set `entityTerms` to filter by category.", "items": { "type": "string" } }, "entityTerms": { "title": "Which portfolio_entries taxonomy terms to scrape", "uniqueItems": true, "type": "array", "description": "Select which portfolio_entries terms to include when no `startUrls` are given. Default `jobs` returns ~6 paid vacancies. Other useful terms: `volunteering`, `get-support`, `get-involved`, `leadership`, `networks`, `advertise`, `podcast`, `membership`.", "items": { "type": "string", "enum": [ "jobs", "volunteering", "get-support", "get-involved", "leadership", "networks", "advertise", "podcast", "membership" ] }, "default": [ "jobs" ] }, "enrichTaxonomies": { "title": "Embed taxonomies + featured media", "type": "boolean", "description": "When enabled (recommended), each row carries decoded `portfolio_entries` term names (split into `categories` vs `locations`) plus featured image URL. Uses WP-JSON `_embed` — no extra HTTP requests.", "default": true }, "postedWithinHours": { "title": "Only rows posted in the last N hours", "minimum": 0, "type": "integer", "description": "Filters on each row's posted date. Leave 0 (default) to return every live vacancy regardless of age — recommended, since CFY only posts a handful of jobs per week. Set 24 for the last day, 72 for the last 3 days, etc. Rows whose source has no posted date are always kept.", "default": 0 }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on rows pushed. ~6 jobs live; whole portfolio is 43 items.", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum WP-JSON pages fetched in parallel.", "default": 5 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Minimum WP-JSON pages fetched in parallel.", "default": 1 }, "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": "Site does not anti-bot — proxy optional.", "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 } } } } } } } } } }