Resume Parser
Education parsing

Education Extraction

Degrees, schools and years extracted from PDF resumes

Get API keyView documentation

Parse degrees, schools, years and academic notes from PDF resumes. Degrees are kept as written.

How it works

  1. 1

    Education section identification

    The parser finds education content regardless of the heading, such as "Education", "Academic Background", or a heading in another language.

  2. 2

    Degree as written

    Each entry returns the degree name as written on the resume. "MSc Information Technology" stays as it is instead of being renamed.

  3. 3

    School names as written

    School names are kept as written, from "University of Oxford" to "Aalto-yliopisto", so you can match them against your own data.

  4. 4

    Years and notes

    Years go into year and endYear. Other details, like honors, thesis title or exchange semesters, go into notes.

Key Benefits

Any institution

No predefined institution database is needed. The school field contains the name as written on the resume.

Original wording kept

Resumes write the same degree in many ways: "BSc", "B.Sc.", "Bachelor of Science". The degree field keeps what the candidate wrote, and you can normalize it in your own system.

Academic notes

The notes field holds supplementary information such as honors or thesis titles, so recruiters don't have to re-read the resume for them.

Location per entry

Each education entry can include a location when the resume lists one.

Code examples

API response (data.educations)json
{
  "educations": [
    {
      "degree": "MSc Computer Science",
      "school": "Example University",
      "year": "2016",
      "endYear": "2018",
      "notes": "Thesis: Distributed consensus in heterogeneous networks",
      "location": "Helsinki, Finland"
    },
    {
      "degree": "BSc Software Engineering",
      "school": "Aalto University",
      "year": "2013",
      "endYear": "2016",
      "notes": "Exchange semester at TU Berlin",
      "location": "Espoo, Finland"
    }
  ],
}

Technical Details

Education parsing is done by the same language model that handles the rest of the resume, so entries are understood in the context of the whole document. Each entry has degree, school, year, endYear, notes and location. year and endYear are returned as strings. The API is hosted on Hetzner in Helsinki, Finland; /v1/parse does not store the PDF or the parsed result, and resume text is processed by OpenAI (US) as a subprocessor.

Questions

Frequently asked questions

Each entry in the educations array includes: degree (as written), school, year, endYear, notes and location (or null). year and endYear are strings.

Degrees are kept as written, so it works with any national system. It does not convert between systems: a German "Diplom-Ingenieur" stays "Diplom-Ingenieur".

There is no separate certifications field. Test with resumes from your applicant pool to see how your typical certification sections come out.

There is no separate GPA field. When a resume lists honors or other academic details with an education entry, they go into the notes text.

Related pages

Features

Work Experience Extraction

Parse job titles, organizations, dates and role descriptions from PDF resumes. Handles "Present" dates and overlapping roles.

Features

Skill Extraction API

Get each role's description, with the skills used, tied to the job where they were used. PDF to structured JSON with one API call.

Solutions

Resume Parser for Staffing Agencies

Turn candidate CVs into ATS-ready JSON with one API call. Contact details, work history, education, and languages. Prepaid credits that don't expire. 50 free parses per month.

Features

PDF Resume Parser

Parse single-column and multi-column PDF resumes into structured JSON with one API call. PDF up to 5 MB. Parsing is synchronous and can take up to 60 seconds.

Test education extraction

50 free parses per month. Parse resumes from international candidates and check the degrees, schools and years.

Get API key