Resume Scanner is a Python-based tool that analyzes resumes (in PDF or DOCX format) and extracts key information into a structured JSON format. It uses OpenAI's language model to intelligently parse resume content and organize it into categories such as personal information, education, skills, experience, and certifications.
Before you begin, ensure you have met the following requirements:
Clone this repository:
git clone https://github.com/yourusername/resume_scanner.git
cd resume_scanner
Install the required packages:
pip install PyPDF2 python-docx langchain openai
Set up your OpenAI API key as an environment variable:
export OPENAI_API_KEY='your-api-key-here'
Replace 'your-api-key-here' with your actual OpenAI API key.
To use Resume Scanner, follow these steps:
Place your resume file (PDF or DOCX) in the project directory or remember its path.
Run the script with the path to your resume file as an argument:
python resume_scanner.py path/to/your/resume.pdf
or
python resume_scanner.py path/to/your/resume.docx
The script will analyze the resume and output the structured data to the console. It will also save the results in a JSON file named <your_resume_name>_analysis.json
in the same directory as your resume.
The output JSON will have the following structure:
{
"name": "John Doe",
"phone_number": "123-456-7890",
"education": [
"Bachelor of Science in Computer Science, XYZ University, 2015-2019"
],
"skills": [
"Python",
"Machine Learning",
"Data Analysis"
],
"experience": [
"Software Engineer, ABC Corp, 2019-Present",
"Intern, DEF Tech, Summer 2018"
],
"certifications": [
"AWS Certified Developer",
"Google Cloud Professional Data Engineer"
]
}
Contributions to Resume Scanner are welcome. Please feel free to submit a Pull Request.
This project uses the following license: MIT License.
If you want to contact me, you can reach me at sohammhatre521@gmail.com
.