# AU Job Description Parser - Skills, Seniority & Tooling (`data_lattice_au/jd-keyword-extractor`) Actor Turn raw job descriptions into structured market intelligence. Batch-parses data, analytics, BI, ML and AI JDs and returns skill tags, seniority, years required and tooling - ready to feed into dashboards, talent maps or pricing models. Cents per JD; thousands per run. - **URL**: https://apify.com/data\_lattice\_au/jd-keyword-extractor.md - **Developed by:** [data\_lattice](https://apify.com/data_lattice_au) (community) - **Categories:** Jobs, Automation - **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $20.00 / 1,000 results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Data Jobs - JD Keyword Extractor (AU) Turn raw job descriptions into structured market intelligence. Batch-parses data, analytics, BI, ML and AI JDs and returns skill tags, seniority, years required and tooling - ready to feed into dashboards, talent maps or pricing models. ### What this is for Recruitment agencies, salary benchmarkers, talent dashboards and research teams all need to do the same thing: take a pile of raw JD text and turn it into structured fields. Doing this in-house with regex spaghetti is a maintenance nightmare; doing it with an LLM is slow and expensive. This Actor uses the same 136-skill data-sphere taxonomy that powers the rest of the Data Lattice portfolio, plus a small inference layer for seniority and years-required, to parse JDs in under 100ms each. Submit 1 JD or 10,000 - same per-item price. ### How this helps you | You are a... | You use this to... | |---|---| | Recruitment agency | Bulk-parse a week of JDs into a structured spreadsheet for desk reporting | | Salary benchmarker | Tag every JD in your panel with skills + seniority before joining to salary data | | Career-tech / EdTech | Automatically classify the listings on your jobs page so users can filter by skill | | Talent intelligence team | Feed structured JD parses into your competitive-hiring dashboard | | Researcher | Build a structured corpus from raw JDs for academic / industry analysis | ### Output (one row per JD) ```jsonc { "jd_index": 0, "skills": ["Python","SQL","Snowflake","dbt","Airflow"], "tooling": ["Snowflake","dbt","Airflow"], "seniority": "Senior", "years_required": 5, "skill_count": 5 } ```` Full schema in `OUTPUT_SCHEMA.json`. ### Pricing **$0.02 per JD parsed** (PRICE\_PER\_DATASET\_ITEM). One large recruitment batch (1,000 JDs) = $20 of usage. Volume-friendly - designed for agencies parsing in bursts. ### Run it ```json { "jds": [ "Senior Data Engineer needed (Python, Spark, AWS, Snowflake, dbt). 5+ years.", "Junior Analyst - Power BI, SQL, basic Python. Graduate-level OK.", "..." ] } ``` Returns one structured row per input JD, in input order. ### Brand Part of the [Data Lattice](https://datalattice.com.au) portfolio. Uses the same skill taxonomy as the [Skill Intelligence](https://apify.com/data_lattice_au/au-data-skill-intelligence) and [Co-Occurrence API](https://apify.com/data_lattice_au/skill-cooccurrence-api) Actors so outputs are directly comparable across the suite. # Actor input Schema ## `jds` (type: `array`): Array of full job description texts to parse. One element per JD. ## `titles` (type: `array`): Optional parallel array of job titles. titles\[i] corresponds to jds\[i]. Used for seniority detection because the title often contains 'Senior'/'Lead'/'Principal' even when the body doesn't repeat it. Leave empty if titles aren't available - parser will fall back to body-only detection. ## Actor input object example ```json {} ``` # Actor output Schema ## `jd_index` (type: `string`): 0-based index of this JD in the input batch. ## `jd_title` (type: `string`): Job title supplied via the parallel `titles` input array (empty string when not provided). ## `tooling` (type: `string`): Specific named products / platforms (Snowflake, dbt, AWS, Power BI, OpenAI). The 'what stack do they actually use' signal. ## `languages` (type: `string`): Programming languages required (Python, SQL, R, Java, etc). ## `technical_general` (type: `string`): Non-tool technical skills (ML, NLP, RAG, ETL, data governance, embeddings, etc). ## `soft_skills` (type: `string`): Soft / behavioural skills mentioned (communication, leadership, stakeholder management, agile, scrum). Separated from technical signal so buyers can filter. ## `qualifications` (type: `string`): Formal qualifications referenced (Bachelor, Masters, PhD). ## `tooling_count` (type: `string`): Number of distinct tools / platforms detected. ## `languages_count` (type: `string`): Number of distinct programming languages detected. ## `technical_general_count` (type: `string`): Number of non-tool technical skills detected. ## `soft_skills_count` (type: `string`): Number of soft skills detected. ## `skill_count` (type: `string`): Total of tooling + languages + technical\_general (excluding soft skills and qualifications). ## `seniority` (type: `string`): Inferred seniority: Junior / Mid / Senior / Lead / Principal / Manager / Director / Staff / Head / Graduate. ## `years_required` (type: `string`): Years of experience required (0 if not stated). ## `word_count` (type: `string`): JD length in words. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("data_lattice_au/jd-keyword-extractor").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = {} # Run the Actor and wait for it to finish run = client.actor("data_lattice_au/jd-keyword-extractor").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call data_lattice_au/jd-keyword-extractor --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=data_lattice_au/jd-keyword-extractor", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "AU Job Description Parser - Skills, Seniority & Tooling", "description": "Turn raw job descriptions into structured market intelligence. Batch-parses data, analytics, BI, ML and AI JDs and returns skill tags, seniority, years required and tooling - ready to feed into dashboards, talent maps or pricing models. Cents per JD; thousands per run.", "version": "0.48", "x-build-id": "BamzReOlP66F8oVP3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/data_lattice_au~jd-keyword-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-data_lattice_au-jd-keyword-extractor", "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/data_lattice_au~jd-keyword-extractor/runs": { "post": { "operationId": "runs-sync-data_lattice_au-jd-keyword-extractor", "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/data_lattice_au~jd-keyword-extractor/run-sync": { "post": { "operationId": "run-sync-data_lattice_au-jd-keyword-extractor", "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", "required": [ "jds" ], "properties": { "jds": { "title": "JD texts", "type": "array", "description": "Array of full job description texts to parse. One element per JD.", "items": { "type": "string" } }, "titles": { "title": "JD titles (optional, parallel array)", "type": "array", "description": "Optional parallel array of job titles. titles[i] corresponds to jds[i]. Used for seniority detection because the title often contains 'Senior'/'Lead'/'Principal' even when the body doesn't repeat it. Leave empty if titles aren't available - parser will fall back to body-only detection.", "items": { "type": "string" } } } }, "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 } } } } } } } } } } ```