ResumeParser.pro

A CV Parsing API Built for Multilingual Hiring

Most parsers were trained on one-page American resumes. Then a ten-page German academic CV with a photo, a birth date and three languages arrives, and the schema falls apart. This endpoint was built for that document.

Start parsing free Endpoint docs

14-day trial · 100,000 words included · No credit card

CV parsing applies the same extraction technology as resume parsing to CV conventions: longer documents, photos and personal data sections, Europass layouts, academic publication lists and multilingual content. The SharpAPI endpoint handles both document cultures with one schema.

What makes CVs harder — and how this API answers

CV-specific challenges · endpoint behaviour
CV realityHow the parser handles it
Length — 3 to 10+ pages is normal in the EU, UK and academia Per-word pricing, no page limits below 100 MB; long documents parse whole, including publication and project lists
Europass and template layouts Layout-agnostic extraction — tables, sidebars and two-column templates map to the same JSON as free-form text
Personal data sections — birth date, nationality, photo Captured into dedicated fields (candidate_date_of_birth, candidate_nationality) so your platform can store or discard them per policy — and stripped automatically before any match scoring
Mixed languages — French CV, English skills section 80+ languages in one pass; output normalizable to your platform's language
Scanned and photographed documents OCR inside the endpoint: JPG, PNG, TIFF up to 100 MB, no separate OCR fee
Degree systems that do not map to US conventions Controlled vocabularies with “or equivalent” semantics — a Polish magister and a UK MSc both normalize to Master's-level

The same one-call integration

POST /api/v1/hr/parse_resume — a CV is the same call
curl -X POST 'https://sharpapi.com/api/v1/hr/parse_resume' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'file=@lebenslauf.pdf' \
  -F 'language=English'   # normalize German CV content to English output

The response schema is identical to the resume flow — candidate profile, positions, education, skills, languages — so a product serving both markets writes one integration. See the full JSON.

Built for European compliance questions

A CV is personal data by definition, so the vendor questions arrive fast: where is it processed, how long is it kept, who trains on it. The answers here are short. Transient processing: documents live only as long as the parsing job. No model training on customer data, ever. GDPR and Singapore PDPA compliance, SOC 2 Type II certification. The longer version is in our GDPR resume parsing guide.

Questions, answered

Is CV parsing different from resume parsing?

The technology is identical; the documents differ. CVs — the norm in the UK, EU, India and most of the world — run longer, often carry photos, birth dates and multi-page academic sections. A parser built for one-page US resumes chokes on them; this endpoint was trained for both conventions.

Can it parse Europass and multi-page academic CVs?

Yes. Layout-agnostic parsing means Europass templates, two-column designs and 10-page academic CVs all map to the same JSON schema. Per-word pricing also means a long CV costs proportionally — you pay for content, not page count.

Which languages does the CV parser handle?

More than 80, including mixed-language documents like a French CV with an English skills section. Output can be normalized to the language your platform uses.

Does it read scanned or photographed CVs?

Yes — OCR is part of the endpoint. JPG, PNG and TIFF scans up to 100 MB parse through the same call as digital PDFs, with no extra OCR fee.

Where does candidate data go under GDPR?

CVs are processed transiently to produce the JSON output, are never used for model training, and SharpAPI holds SOC 2 Type II certification alongside GDPR and PDPA compliance — the questions an EU data-protection officer asks first.

Further reading