██████╗ ███████╗███████╗██╗   ██╗███╗   ███╗███████╗    ██████╗  █████╗ ██████╗ ███████╗███████╗██████╗
██╔══██╗██╔════╝██╔════╝██║   ██║████╗ ████║██╔════╝    ██╔══██╗██╔══██╗██╔══██╗██╔════╝██╔════╝██╔══██╗
██████╔╝█████╗  ███████╗██║   ██║██╔████╔██║█████╗      ██████╔╝███████║██████╔╝███████╗█████╗  ██████╔╝
██╔══██╗██╔══╝  ╚════██║██║   ██║██║╚██╔╝██║██╔══╝      ██╔═══╝ ██╔══██║██╔══██╗╚════██║██╔══╝  ██╔══██╗
██║  ██║███████╗███████║╚██████╔╝██║ ╚═╝ ██║███████╗    ██║     ██║  ██║██║  ██║███████║███████╗██║  ██║
╚═╝  ╚═╝╚══════╝╚══════╝ ╚═════╝ ╚═╝     ╚═╝╚══════╝    ╚═╝     ╚═╝  ╚═╝╚═╝  ╚═╝╚══════╝╚══════╝╚═╝  ╚═╝

Drop a resume. Get the data. No reading required.

---

❓ What is this?

MAINLY FOR EMPLOYERS Most resume parsers are either locked behind expensive APIs or produce messy, unreliable output. Resume Parser is a lightweight, locally-runnable Streamlit web app that takes any resume — PDF, DOCX, TXT, or plain pasted text — and surgically extracts the information that actually matters.

Once all that information is extracted it is placed in a downloadable CSV file and then it will enable the employer to sort with the needs they want.
They can search the requirements and get the candidates With those particular aspects.
The aspects can vary from candidates who have worked at partcular organization,gone to a certain school,years of experience.....you name any metric you want to filter the candidates with

---

website dashboard

🖼️ Screenshots

📂 Upload Interface	📋 Parsed Output
✏️ Work experience EXTRACTED	📊 Extracted CSV File for downloading

---

⚙️ What it extracts

The parser targets the fields that hiring tools, recruiters, and ATS systems care about most:

┌─────────────────────────────────────────────────────────────┐
│                    EXTRACTED FIELDS                         │
├──────────────────────┬──────────────────────────────────────┤
│  👤  Full Name        │  Detected from resume header         │
│  📧  Email Address    │  Primary contact email               │
│  📍  Location         │  City / Country / Region             │
│  🔗  LinkedIn URL     │  Profile link                        │
│  🌐  Other Links      │  GitHub, portfolio, personal site    │
│  💼  Job Title        │  Current or most recent role         │
│  🏢  Work Experience  │  Companies · Roles · Durations       │
└──────────────────────┴──────────────────────────────────────┘

---

🧠 How the extraction actually works

This isn't a single-method parser — it runs a three-layer hybrid pipeline to maximise accuracy across different resume styles and formats:

INPUT (PDF / DOCX / TXT / Paste)
        │
        ▼
┌───────────────────┐
│  Text Extraction  │  ← PyMuPDF / pdfplumber (PDF) · python-docx (DOCX) · raw string (TXT/paste)
└────────┬──────────┘
         │
         ▼
┌───────────────────┐
│  Regex Layer      │  ← Fast, deterministic pattern matching for emails, URLs, phones
└────────┬──────────┘
         │
         ▼
┌───────────────────┐
│  NLP Layer        │  ← spaCy Named Entity Recognition + NLTK for names, orgs, locations
└────────┬──────────┘
         │
         ▼
┌───────────────────┐
│  AI Refinement    │  ← LLM cleans up ambiguous fields where NLP is uncertain
└────────┬──────────┘
         │
         ▼
  STRUCTURED OUTPUT (displayed in Streamlit UI)

Each layer feeds into the next — regex handles the clear-cut stuff, NLP picks up semantic patterns, and AI fills the gaps.

---

🛠️ Tech Stack

What	How
App Framework	Streamlit
Language	Python 3.10+
PDF Extraction	PyMuPDF · pdfplumber
DOCX Extraction	python-docx
NLP Engine	spaCy · NLTK
AI Layer	Gemini API · OpenAI API
Pattern Matching	Regex (re module)

---

🚀 Running it locally

1. Clone the repo

git clone https://github.com/your-username/resume-parser.git
cd resume-parser

2. Set up a virtual environment

python -m venv venv

# macOS / Linux
source venv/bin/activate

# Windows
venv\Scripts\activate

3. Install dependencies

pip install -r requirements.txt

4. (Optional) Add your API key

If you're using the AI refinement layer, create a .env file:

GEMINI_API_KEY=your_key_here
# or
OPENAI_API_KEY=your_key_here

5. Launch

streamlit run app.py

Visit http://localhost:8501 — that's it.

---

---

🗺️ Features

• PDF, DOCX, TXT upload support
• Raw text paste mode
• Name, email, location, LinkedIn, links extraction
• Job title detection
• Work experience parsing

📄 License

MIT — free to use, modify, and build on.

---