jobscan-cli

JobScan turns any career page into a structured, trackable feed. It uses LLMs to parse job listings and a local SQLite database to track history.

Features

• 🤖 AI Extraction: Parses jobs from any HTML layout using LLM.
• 🔄 Smart Diffing: Highlights new jobs since the last scan.
• ⚡ Fast & Headless: Uses optimized Playwright scraping.
• 🔒 Privacy First: Database and API keys live on your machine.
• 🇧🇩 Pre-loaded: Comes with top 20 BD tech companies ready to scan.

Installation

npm install -g jobscan-cli

Usage

Setup

Configure LLM Api key

$ jobscan init

Add Career Pages

Add the URL of any company's career page.

$ jobscan add https://career.grameenphone.com/job

Scan

Scan all configured career pages to identify new job postings.

$ jobscan

Manage URLs

List or remove tracked pages.

$ jobscan urls
$ jobscan remove https://careers.google.com/jobs
$ jobscan remove --all # Clear all URLs

History

View all previously found jobs.

$ jobscan list
$ jobscan list --company Robi

CLI Reference

| Command | Alias | Description | | -------- | ----------- | ------------------------------------- | | init | | Configure API keys | | add | | Add a new career page URL | | scan | (default) | Scan pages for new jobs | | list | | List all jobs in database | | urls | | List existing URLs | | remove | | Remove a URL or all URLs with --all | | clear | | Reset database or config |

Configuration

Configuration is stored in ~/.jobscan/config.json.

Built With

• Playwright - Browser automation & scraping.
• Gemini / Groq / OpenAI - LLM.
• SQLite - Local database.

License

MIT