Job Listing

Learn how to use MrScraper to extract job postings from real websites for analysis, hiring trends, or app development.

Extracting job listings manually from job boards can be tedious and time-consuming. With MrScraper’s AI Scraper, you can automate this process entirely — providing only a URL and a short prompt describing what to extract.

In this guide, we’ll walk through a real-world example where a recruitment team uses MrScraper to gather and analyze data from a live job board to inform their hiring strategy.

Scenario

Imagine you’re an HR specialist at a growing tech startup planning to hire a Data Scientist.
Before posting your own job, you want to understand:

What skills and qualifications are most in-demand
How other companies describe their Data Scientist roles
Which cities or companies are hiring for similar positions

Step 1: Create a New AI Scraper

Go to your MrScraper Dashboard → click Create Scraper.
Enter the URL: https://www.glassdoor.com/Job/indonesia-data-scientist-jobs-SRCH_IL.0,9_IN113_KO10,25.htm
Choose AI Scraper as your scraper type.
Select Super Mode to get more accurate and structured extraction for job listings.

Step 2: Filter Out

Next, tell the AI exactly what kind of job data you want to capture. The prompt defines both the structure of your results and any filters to apply. For this use case, you can use the following prompt:

Extract only job listings with the job title "Data Scientist" that are suitable for fresh graduates or candidates with a minimum of 2 years of experience, and include required skills details.

For each listing, return these fields:
- Job Title
- Company Name
- Location
- Salary
- Job Type
- Experience Level
- Posted Date
- Job Description
- Required Skills
- Job URL

Filter out any listing that does not include required skills information or requires more than 2 years of experience.

Here’s a sample output:

Scraping Result

{
  "mode": "direct",
  "results": [
    {
      "Salary": null,
      "Job URL": "https://www.glassdoor.com/job-listing/it-data-scientist-apotek-k-24-JV_KO0,17_KE18,29.htm?jl=1009644720583",
      "Job Type": null,
      "Location": "Indonesia",
      "Job Title": "IT Data Scientist",
      "Posted Date": "30d+",
      "Company Name": "Apotek K 24",
      "Job Description": "Mengolah dan menganalisis data besar dari berbagai sumber (POS, CRM, marketplace, dll) untuk menemukan pola dan insight bisnis. Mengembangkan model statistik dan machine learning (supervised dan unsupervised) untuk kebutuhan forecasting, recommendation, atau clustering. Melakukan feature engineering dan model evaluation untuk memastikan performa model optimal. Berkolaborasi dengan tim Data Engineering untuk integrasi pipeline data dan deployment model. Berkoordinasi dengan tim BI Analyst untuk penerjemahan hasil analitik ke dalam dashboard dan laporan bisnis. Melakukan eksperimen model (A/B testing, hyperparameter tuning) dan dokumentasi hasilnya. Menjaga data quality, model reproducibility, serta model governance sesuai kebijakan perlindungan data perusahaan. Minimum Qualifications: Menguasai Python (NumPy, Pandas, Scikit-learn, TensorFlow/PyTorch, Matplotlib/Seaborn). Memahami konsep statistik, machine learning, dan data preprocessing. Pengalaman dengan SQL dan query optimization. Familiar dengan tools visualisasi (Power BI, Tableau, atau setara). Pengalaman dalam mengelola version control (Git) dan ML lifecycle tools (MLflow, DVC, dsb) menjadi nilai tambah. Memahami time series forecasting, NLP, atau recommender system menjadi nilai plus. Komunikatif dan kolaboratif lintas tim (Engineering, BI, Business Unit). Kompas Gramedia, through its more than 50 years of history, is striving for one goal: enlightening and empowering Indonesia. To ensure that we are able to serve the nation for another 50 years, we are undergoing a digital transformation; strengthening and expanding our solid business pillars by developing new digital business initiatives. Our vision is to enlight all the people in Indonesia with all the knowledge we have.",
      "Required Skills": [
        "NumPy",
        "Pandas",
        "Scikit-learn",
        "TensorFlow",
        "PyTorch",
        "Matplotlib",
        "Seaborn",
        "Python",
        "machine learning",
        "data preprocessing",
        "dengan SQL",
        "query optimization",
        "Power BI",
        "Tableau",
        "Git",
        "MLflow",
        "DVC",
        "time series forecasting",
        "NLP",
        "Engineering",
        "BI",
        "Business Unit"
      ],
      "Experience Level": "2 years"
    }
  ]
}

Tip

Some job sites show different listings by region. Use MrScraper’s proxy to view results from other countries, or your own proxy if needed.
Schedule your scraper to run daily or weekly to keep your job data up to date.

Step 3: Use the Extracted Data

Once you’ve collected the job listings, you can export and use the data directly from the dashboard in your preferred format.

You can use these data for:

Job posting optimization: Identify trending keywords or skills that attract top candidates.
Competitor analysis: See how similar companies describe their open roles.
Internal reporting: Share hiring trends or skill gaps with your HR or analytics team.

Job Listing

Scenario

Step 1: Create a New AI Scraper

Step 2: Filter Out

Step 3: Use the Extracted Data

On this page