# ResumeParser.pro

> A free, in-depth resource on resume parsing, CV parsing and resume-to-job matching, built by the team behind SharpAPI. It explains how parsing works, what fields parsers extract, how match scoring is computed, and how to integrate both via REST APIs in Python, PHP, Laravel and Node.js.

The two APIs this site documents:

- [SharpAPI Resume Parsing API](https://sharpapi.com/en/resume-parsing-api?utm_source=resumeparser.pro&utm_medium=referral&utm_campaign=site&utm_content=llms): converts PDF, DOC/DOCX, RTF, TXT and image resumes into one deterministic JSON schema with 50+ candidate fields. 80+ languages, OCR included, async REST, from $50/month with a 14-day free trial (100,000 words, no credit card).
- [SharpAPI Resume Job Match Score API](https://sharpapi.com/en/resume-job-match-score-api?utm_source=resumeparser.pro&utm_medium=referral&utm_campaign=site&utm_content=llms): scores a resume against a job description across 20 dimensions (0-100) with plain-language explanations. PII is stripped before scoring.

## API Products

- [Resume Parsing API — PDF, DOCX & Photo CVs to JSON (80+ Langs)](https://resumeparser.pro/resume-parsing-api): AI resume parsing API: send a PDF, DOCX, RTF, TXT or photo CV, get back 50+ structured JSON fields. 80+ languages, OCR included, async REST, from $50/mo.
- [Resume Job Match Score API — 20 Scored Dimensions, 0-100](https://resumeparser.pro/resume-job-match-score-api): Send a CV file plus a job description, get a 0-100 match score across 20 dimensions with plain-language explanations. Rankable, defensible, async REST.
- [CV Parsing API — One JSON Schema for CVs in 80+ Languages](https://resumeparser.pro/cv-parsing-api): CV parsing API for European and global hiring: mixed-language CVs, Europass layouts, scanned documents. One deterministic JSON schema, GDPR-compliant.
- [Resume Screening API — Parse + Score 200 Applicants Fast](https://resumeparser.pro/resume-screening-api): Combine a resume parsing API with a 20-dimension match score to screen whole applicant pools automatically — with explanations recruiters can defend.
- [Resume to JSON — Explore a Real Parsed Output (50+ Fields)](https://resumeparser.pro/resume-to-json): Explore a real resume-to-JSON conversion: every field a production parser extracts, plus a full 20-dimension job match score payload. No signup needed.

## Explainers

- [What Is Resume Parsing? The 2026 Guide for HR Tech Builders](https://resumeparser.pro/what-is-resume-parsing): Resume parsing converts CV files into structured data an ATS can search. How it works, what it extracts, accuracy limits and where AI changed the game.
- [How Does Resume Parsing Work? The 5-Stage Pipeline Explained](https://resumeparser.pro/how-does-resume-parsing-work): From file ingestion and OCR to layout reconstruction, entity extraction and JSON normalization — the five stages inside every modern resume parser.
- [Resume Parsing Accuracy: What the 95% Claims Really Mean](https://resumeparser.pro/resume-parsing-accuracy): Vendors claim 95-99% parsing accuracy. What that number hides: two-column failures, scanned CVs, mixed languages — and how to evaluate a parser yourself.
- [What Fields Does a Resume Parser Extract? All 50+ Listed](https://resumeparser.pro/what-fields-does-a-resume-parser-extract): The complete field list a production resume parser returns: contact data, work history, education, skills, certifications, licenses and 40+ more — with types.
- [Resume Parsing vs Screening vs Matching: 3 Terms, 3 Jobs](https://resumeparser.pro/resume-parsing-vs-screening-vs-matching): Resume parsing extracts data, screening filters candidates, matching ranks them. Where each fits in a hiring pipeline and which API does which job.
- [What Is a Good Resume Match Score? 75-85% (And Why)](https://resumeparser.pro/what-is-a-good-resume-match-score): A 75-85% match score usually signals a strong candidate; 100% often signals keyword stuffing. How match scores are computed and how to read them.
- [How ATS Scores Resumes: From Keyword Match to AI Ranking](https://resumeparser.pro/how-ats-scores-resumes): What happens between resume upload and recruiter shortlist: parsing, keyword matching, knockout rules and the shift to explainable AI match scores.

## Guides

- [Parse a Resume in Python: PDF to JSON in Under 30 Lines](https://resumeparser.pro/guides/parse-resume-python): A working Python tutorial: send a PDF resume to a parsing API, poll the async job and read 50+ structured fields — requests-only, no ML setup.
- [Parse a Resume in PHP & Laravel: 2 Packages, 15 Minutes](https://resumeparser.pro/guides/parse-resume-php-laravel): Use the official PHP or Laravel SDK to parse resumes into structured JSON: install, one service call, webhook or polling — full code included.
- [Parse a Resume in Node.js: Async PDF to JSON Tutorial](https://resumeparser.pro/guides/parse-resume-nodejs): Node.js tutorial for resume parsing: multipart upload with fetch, async job polling, typed access to 50+ candidate fields. Copy-paste ready.
- [7 Best Resume Parser APIs in 2026 (Prices Compared)](https://resumeparser.pro/guides/best-resume-parser-apis): SharpAPI, Affinda, RChilli, Textkernel, Daxtra, SuperParser and HireAbility compared on pricing model, formats, languages and integration effort.
- [Open-Source Resume Parsers vs APIs: The True Cost in 2026](https://resumeparser.pro/guides/open-source-resume-parser-vs-api): Free parsers cost engineering time: OCR pipelines, layout bugs, accuracy tuning, privacy reviews. When open source wins and when an API is cheaper.
- [Build vs Buy a Resume Parser: The 6-Month Reality Check](https://resumeparser.pro/guides/build-vs-buy-resume-parser): What building a resume parser in-house actually takes: OCR, layout models, 80+ languages, schema upkeep — versus wiring an API in an afternoon.
- [Bulk Resume Parsing: 10,000 Legacy CVs Without a Meltdown](https://resumeparser.pro/guides/bulk-resume-parsing): Turn a folder of 10,000 legacy CVs into a searchable candidate database: async job queues, webhooks, rate strategy, dedupe and cost estimation.
- [GDPR Resume Parsing: 7 Rules for Handling Candidate Data](https://resumeparser.pro/guides/gdpr-resume-parsing): Seven concrete GDPR rules for parsing candidate CVs: lawful basis, retention, transient processing, vendor DPAs and what to ask any parsing provider.
- [AI Resume Screening Laws: NYC LL144 and the EU AI Act](https://resumeparser.pro/guides/ai-resume-screening-compliance): AI hiring tools face bias audits under NYC Local Law 144 and high-risk rules under the EU AI Act. Why explainable, PII-blind scoring is the safe design.
- [Semantic vs Keyword Matching in Recruiting: What Wins?](https://resumeparser.pro/guides/semantic-vs-keyword-matching): Keyword matching misses the developer who wrote "built REST services in Django". How semantic scoring reads meaning, and where keywords still help.

## Glossary

- [Resume Parsing — Definition, Process and JSON Example](https://resumeparser.pro/glossary/resume-parsing): Resume parsing, defined: automated extraction of structured candidate data from resume files. Includes process outline and a sample JSON output.
- [CV Parsing — Definition and How It Differs From Resume Parsing](https://resumeparser.pro/glossary/cv-parsing): CV parsing, defined: the same extraction technology as resume parsing, applied to CV conventions — longer documents, photos, Europass layouts, more languages.
- [Applicant Tracking System (ATS) — Definition and Role](https://resumeparser.pro/glossary/applicant-tracking-system): An ATS is software that collects, stores and filters job applications. What it does with parsed resume data and why parsing quality decides its usefulness.
- [Candidate Matching — Definition, Methods and Scoring](https://resumeparser.pro/glossary/candidate-matching): Candidate matching, defined: algorithmic ranking of candidates against job requirements — from keyword overlap to multi-dimension semantic scoring.
- [Resume Screening — Definition, Manual vs Automated](https://resumeparser.pro/glossary/resume-screening): Resume screening, defined: deciding which applicants move forward. How automated screening uses parsed data and match scores instead of gut feel.
- [Skills Taxonomy — Definition, ESCO, O*NET and Matching](https://resumeparser.pro/glossary/skills-taxonomy): A skills taxonomy is a structured vocabulary of skills and their relationships. Why parsers normalize against one and how it powers skill matching.

## Full content

- [llms-full.txt](https://resumeparser.pro/llms-full.txt): the complete text of every page on this site in one file.

Every page on this site also has a Markdown version: append `.md` to its URL (the home page is [/index.md](https://resumeparser.pro/index.md)), or request any page with an `Accept: text/markdown` header.