This notebook helps recruiters and hiring managers to identify the most-matched resumes very quickly and accelerate finding the top talent. This code can read a huge amount of PDF files (resumes) and sort them based on the most related keywords. Generally, this notebook can be implemented not only for resumes but also for any PDFs to scan and find your related keywords.
1- Install PyPDF2: !pip install PyPDF2
2- Move all the resumes in a same directory and define your directory path in: directory_path
3- Replace your custom keywords in: keywords
4- Run the cell
In the output you will see the sorted resumes based on the most related keywords and also the name of resumes, eg: Resume_1.pdf, Resume_2.pdf, Resume_3.pdf and so on.
This notebook is under license and any publishing without referring to my repository is prohibited!
Developer: Melanee