# Job Post Parser — Structured Jobs & Skills (AI) (`noniner/b2b-job-post-parser`) Actor

Turn any job posting URL or pasted text into clean structured data: title, seniority, skills, requirements, responsibilities, salary, location, remote policy and tech stack — plus an AI clarity score. For recruiters, job boards and talent-market analytics.

- **URL**: https://apify.com/noniner/b2b-job-post-parser.md
- **Developed by:** [Fredrik Hansson](https://apify.com/noniner) (community)
- **Categories:** Jobs, AI, Developer tools
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $100.00 / 1,000 job parseds

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/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Job Post Parser — Structured Jobs & Skills (AI)

**Turns any job posting into clean, structured data your systems can actually use.** Hand it a job posting URL or paste the raw job description text, and this Actor returns one tidy JSON record per job: normalized title, seniority, department, employment type, company, location, remote policy, salary range, **skills**, **tech stack**, requirements, responsibilities, nice-to-haves, years of experience — plus an **AI clarity score** and a list of red flags.

You bring job URLs or text. It hands back structured jobs ready for your ATS, job board, or analytics warehouse.

***

### The flow

```
1. Give a job URL or paste text   2. Fetch + clean + AI parse       3. Get a structured job
   job posting URL  ──────────►       got-scraping → cheerio   ──►     title · seniority · skills
   or raw description text             → OpenAI (grounded)             salary · tech stack · clarity
```

1. **Give it job posting URLs** (`jobUrls`) — the Actor fetches each page and strips it to clean text — **or paste raw job description text** (`jobTexts`) when you already have the copy. Mix both in one run.
2. **AI parses each job** (OpenAI `gpt-4o-mini`, a fast, low-cost model), grounded strictly in the supplied text. Anything not stated comes back `null`; every field is written in English even if the source isn't.
3. **Get one structured record per job**, charged once via a single pay-per-event — ready to push straight into a database, spreadsheet or pipeline.

***

### What you get per job

For every job posting, the Actor extracts:

1. **Title & level** — `jobTitle`, `normalizedTitle` (a clean canonical title like *"Senior Backend Engineer"*), `seniority` (`intern` / `junior` / `mid` / `senior` / `lead` / `manager` / `director` / `exec`), `department`, `employmentType`.
2. **Company & location** — `companyName`, `location`, `remotePolicy` (`onsite` / `hybrid` / `remote`).
3. **Compensation** — `salaryMin`, `salaryMax`, `salaryCurrency`, `salaryPeriod` (`year` / `month` / `hour`) — only when disclosed.
4. **Skills & stack** — `skills` (normalized skill names) and `techStack` (languages, frameworks, tools, platforms).
5. **The fine print** — `requirements`, `responsibilities`, `niceToHaves`, `yearsExperienceMin`.
6. **Quality signal** — `clarityScore` (0–100: how clear, complete and candidate-friendly the posting is), `clarityNotes` (one sentence), and `redFlags` (e.g. *"no salary disclosed"*, *"vague responsibilities"*, *"unrealistic requirements"*).

Every field is grounded only in the posting — no invented facts, `null` when not stated.

***

### Three ways people use it

- **Recruiting ops & ATS enrichment** — normalize messy inbound job descriptions into a consistent schema, auto-tag seniority, department and skills, and flag low-clarity postings before they go live. Enrich every req in your applicant tracking system with structured skills and salary bands.
- **Job board normalization** — ingest listings from dozens of sources and **parse job descriptions** into one clean schema, so filters by title, seniority, remote policy, location and tech stack all work across your whole catalogue.
- **Talent-market & skills analytics** — turn thousands of postings into a structured dataset for skills-demand trends, **salary benchmarking data**, hiring-signal tracking, and competitive talent intelligence. Perfect feedstock for dashboards and data warehouses.

***

### Input

| Field | Type | Notes |
|---|---|---|
| `jobUrls` | array | Job posting URLs to fetch and parse. One per line. |
| `jobTexts` | array | Alternative/addition to URLs — paste raw job description text directly, one job per entry. |
| `maxResults` | integer | Cap how many jobs to process across URLs + texts. Default `200`. |
| `maxConcurrency` | integer | Jobs processed in parallel. Default `5`. |
| `model` | string | Override the OpenAI model. Default `gpt-4o-mini`. |

Provide **at least one** of `jobUrls` or `jobTexts`.

#### Minimal input example

```json
{
  "jobUrls": [
    "https://example.com/careers/senior-backend-engineer"
  ],
  "jobTexts": [
    "Senior Backend Engineer (Remote, US). 5+ years in Go and PostgreSQL to build our payments platform. Requirements: Go, PostgreSQL, Kubernetes, AWS. Salary: $160,000 - $200,000 per year."
  ]
}
```

***

### Output example

```json
{
  "source": "text",
  "url": null,
  "jobTitle": "Senior Backend Engineer",
  "normalizedTitle": "Senior Backend Engineer",
  "seniority": "senior",
  "department": "Engineering",
  "employmentType": "full-time",
  "companyName": null,
  "location": "United States",
  "remotePolicy": "remote",
  "salaryMin": 160000,
  "salaryMax": 200000,
  "salaryCurrency": "USD",
  "salaryPeriod": "year",
  "skills": ["Go", "PostgreSQL", "Kubernetes", "AWS", "API design", "Mentoring"],
  "techStack": ["Go", "PostgreSQL", "Kubernetes", "AWS"],
  "requirements": ["5+ years backend experience", "Go", "PostgreSQL", "Kubernetes", "AWS"],
  "responsibilities": ["Design APIs", "Build the payments platform", "Mentor junior engineers"],
  "niceToHaves": ["Stripe experience"],
  "yearsExperienceMin": 5,
  "clarityScore": 82,
  "clarityNotes": "Clear role, stack and salary, though the company name and benefits are not stated.",
  "redFlags": []
}
```

Records that come from a URL have `"source": "url"` and the fetched `url`. Jobs that could not be fetched or parsed come back with `success: false` and an `error` message.

***

### Pay-per-event pricing

This Actor uses **pay-per-event** billing with a single event:

| Event | Charged when | Price |
|---|---|---|
| `job-parsed` | Once per job posting parsed into structured fields — title, seniority, skills, salary, tech stack and an AI clarity score. | **$0.10** |

The Actor logs its OpenAI token usage and the estimated AI cost per job at the end of every run, so the event price always stays safely above the model cost (typically a fraction of a cent per job).

***

### Setup

The AI layer calls the OpenAI API. Set the environment variable / secret **`OPENAI_API_KEY`** on the Actor. Without it, the run fails fast with a clear message.

***

### Use it from an AI agent (Apify MCP server)

This Actor is available through the [Apify MCP server](https://mcp.apify.com), so AI agents (Claude, ChatGPT, or anything that speaks MCP) can call it as a tool — hand it `jobUrls` or `jobTexts`, and read back fully structured jobs — with no custom integration code.

***

### Run it locally

```bash
npm install
## put your input in storage/key_value_stores/default/INPUT.json
export OPENAI_API_KEY=sk-...
apify run -p
```

***

### Chain it

**This Actor is a building block in the No Niner B2B suite.** Wire it to the next step with no code in the **Integrations** tab (trigger: *Run succeeded* → start the next Actor), or run them in sequence.

- ⬆️ Upstream: [Career Site Jobs API](https://apify.com/noniner/career-site-jobs-api) and [B2B Hiring Signal Tracker](https://apify.com/noniner/b2b-hiring-signal-tracker) — pull the postings, then parse each into structured fields.
- 🔁 Use with: [B2B Talent Sourcing Brief](https://apify.com/noniner/b2b-talent-sourcing-brief) — turn parsed roles into recruiter account intel.

***

### Related actors

- [Career Site Jobs API](https://apify.com/noniner/career-site-jobs-api) — Pull every open role from a company's ATS (Greenhouse, Lever, Workday and more) into one clean job schema.
- [B2B Hiring Signal Tracker](https://apify.com/noniner/b2b-hiring-signal-tracker) — Track which companies are hiring and for what, turning job-posting activity into buying/growth signals.
- [B2B Talent Sourcing Brief](https://apify.com/noniner/b2b-talent-sourcing-brief) — Turn a role into a sourcing brief: target companies, skills and outreach angles for recruiters.
- [GitHub Candidate Scorer](https://apify.com/noniner/github-candidate-scorer) — Score and rank GitHub developers against a role for technical sourcing.

***

**Part of the [No Niner](https://noniner.io) toolkit** — no-code web scraping, enrichment & AI data tools, all pay-per-use. Browse the full set at **[noniner.io](https://noniner.io)**.

# Actor input Schema

## `jobUrls` (type: `array`):

Job posting URLs to fetch and parse. One per line.

## `jobTexts` (type: `array`):

Paste raw job description text directly (alternative or addition to URLs). One job per entry.

## `maxResults` (type: `integer`):

Max jobs to parse across URLs and texts. One pay-per-event charge per job parsed.

## `maxConcurrency` (type: `integer`):

How many jobs to process in parallel.

## `model` (type: `string`):

Override the model (default gpt-4o-mini).

## `datasetId` (type: `string`):

Optional. Read the inputs from a previous Actor run's dataset — for no-code chaining via the Integrations tab.

## `datasetField` (type: `string`):

Which dataset field to read. Leave blank to auto-detect.

## Actor input object example

```json
{
  "jobUrls": [
    "https://boards.greenhouse.io/openai/jobs/4567890"
  ],
  "maxResults": 200,
  "maxConcurrency": 5
}
```

# Actor output Schema

## `jobs` (type: `string`):

All parsed job records in the default dataset.

# 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 '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "jobUrls": [
        "https://boards.greenhouse.io/openai/jobs/4567890"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("noniner/b2b-job-post-parser").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 '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "jobUrls": ["https://boards.greenhouse.io/openai/jobs/4567890"] }

# Run the Actor and wait for it to finish
run = client.actor("noniner/b2b-job-post-parser").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "jobUrls": [
    "https://boards.greenhouse.io/openai/jobs/4567890"
  ]
}' |
apify call noniner/b2b-job-post-parser --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,noniner/b2b-job-post-parser"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/Ecelw6jwOvPrv0LN7/builds/8FXV0wSzS7JlfObXQ/openapi.json