{ "openapi": "3.0.1", "info": { "title": "Python Jobs Scraper (python.org)", "description": "Python jobs scraper for the python.org Job Board: export every Python job listing (title, company, location, categories, date, link) to JSON, CSV or Excel. Public pages only, no login.", "version": "0.1", "x-build-id": "XAIGPVDAhQQxJMafa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/compass_lab~python-job-board-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-compass_lab-python-job-board-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/compass_lab~python-job-board-scraper/runs": { "post": { "operationId": "runs-sync-compass_lab-python-job-board-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/compass_lab~python-job-board-scraper/run-sync": { "post": { "operationId": "run-sync-compass_lab-python-job-board-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "keywords": { "title": "Keywords", "type": "array", "description": "Keep jobs whose title (and description, when 'Include description' is on) contains any of these words. Case-insensitive.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Drop jobs whose title (and description, when on) contains any of these words.", "items": { "type": "string" } }, "location": { "title": "Location", "type": "string", "description": "Keep jobs whose location contains this text, e.g. 'Berlin' or 'United States'." }, "remoteOnly": { "title": "Remote only", "type": "boolean", "description": "Keep only remote jobs (location says Remote/Anywhere, or the source marks the job as remote).", "default": false }, "postedAfter": { "title": "Posted after", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Keep jobs posted on or after this date (YYYY-MM-DD). Jobs without a date are kept." }, "onlyNewSinceLastRun": { "title": "Only new jobs since the last run", "type": "boolean", "description": "For scheduled runs: skip jobs this same input already returned. The IDs are kept in a named key-value store; delete it to start over.", "default": false }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "Maximum number of items to return (0 = unlimited). You pay per result, so this also caps the cost.", "default": 50 }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Python.org Job Board list pages to scrape (e.g. https://www.python.org/jobs/ or https://www.python.org/jobs/location/remote/).", "default": [ { "url": "https://www.python.org/jobs/" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "type": "integer", "description": "Maximum listing pages to follow per start URL (pagination).", "default": 5 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum parallel requests (politeness; 1-10).", "default": 2 }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 250, "type": "integer", "description": "Minimum delay between requests, in milliseconds (at least 250).", "default": 1000 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }