CV Analysis Tool

A PyQt5-based desktop application that allows jjusers to analyze CVs (PDF/DOCX) with text extraction, keyword detection, and AI-assisted insights.

Features

• Upload and analyze CVs (PDF/DOCX).
• Extract text and detect important keywords.
• Simple and clean PyQt5 user interface.
• Export results for reporting.

---

Installation

1. Clone the repository

git clone https://github.com/yourusername/CV_Analyzer.git
cd CV_Analyzer

2. Create virtual environment

python -m venv venv
venv\Scripts\activate   # (Windows)
# or
source venv/bin/activate  # (Linux/Mac)

3. Upgrade pip & install requirements

python -m pip install --upgrade pip setuptools wheel
pip install -r requirements.txt

4. Install Tesseract-OCR (for text extraction)

This project uses Tesseract OCR for extracting text from CVs.

Windows: Download the installer from UB Mannheim builds

(Recommended version: tesseract-ocr-w64-setup-5.x.x.exe)

.\Tesseract-OCR\

5. Fix spaCy language models

After installing requirements, you’ll notice two directories inside venv\Lib\site-packages:

en_core_web_lg-3.8.0/

en_core_web_trf-3.8.0/

⚠️ spaCy sometimes installs them as versioned subfolders instead of proper package folders. To fix this:

Go to your venv site-packages directory:

venv\Lib\site-packages

Move the contents of: en_core_web_lg/en_core_web_lg-3.8.0/ → into en_core_web_lg/ en_core_web_trf/en_core_web_trf-3.8.0/ → into en_core_web_trf/

Delete the empty folders: en_core_web_lg-3.8.0 en_core_web_trf-3.8.0

This ensures spaCy can properly import the models: import en_core_web_lg import en_core_web_trf

Usage

python CV_Analyzer.py

License

This project is licensed under the MIT License - see the LICENSE file for details.