https://github.com/boshyxd/resumeocr
Python tool that converts multiple resume images to searchable text files using OCR technology
https://github.com/boshyxd/resumeocr
conversion ocr ocr-python ocr-recognition python resume scraper
Last synced: 13 days ago
JSON representation
Python tool that converts multiple resume images to searchable text files using OCR technology
- Host: GitHub
- URL: https://github.com/boshyxd/resumeocr
- Owner: boshyxd
- Created: 2024-07-01T16:29:43.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-12-28T18:44:56.000Z (over 1 year ago)
- Last Synced: 2025-02-22T11:32:17.842Z (over 1 year ago)
- Topics: conversion, ocr, ocr-python, ocr-recognition, python, resume, scraper
- Language: Python
- Homepage:
- Size: 5.59 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ResumeOCR
ResumeOCR is a Python script that automates the process of converting multiple resume images (PNG format) to text files using Optical Character Recognition (OCR).
## Description
This tool scans a specified input folder for PNG images of resumes, uses OCR to extract the text content, and saves each result as a separate text file in an output folder. It's designed to help streamline the process of digitizing and managing large numbers of resume images.
## Features
- Batch processing of multiple PNG files
- Automatic naming of output text files
- Configurable input and output directories
## Requirements
- Python 3.x
- google-generativeai
- Pillow (PIL)
## Usage
1. Place resume image files (PNG, JPG, JPEG) in `~/Documents/ResumePng/`
2. Create a .env file with your Gemini API key:
```
GEMINI_API_KEY=your_api_key_here
```
3. Run the script
4. Find the combined results in `~/Documents/ResumeDump/combined_results.txt`