Create a resume tailoring tool using Python

Here is a simple yet effective Resume Tailoring Tool built with Python. This tool allows users to input a job description and their resume text, then it matches keywords from the job description with the resume and highlights missing or underrepresented skills and keywords, helping users tailor their resume accordingly.

python
CopyEdit
import re
from collections import Counter
from sklearn.feature_extraction.text import CountVectorizer
from difflib import SequenceMatcher

def clean_text(text):
    # Lowercase, remove special characters
    text = text.lower()
    text = re.sub(r'[^a-zs]', '', text)
    return text

def extract_keywords(text, top_n=30):
    text = clean_text(text)
    vectorizer = CountVectorizer(stop_words='english')
    X = vectorizer.fit_transform([text])
    word_counts = zip(vectorizer.get_feature_names_out(), X.toarray()[0])
    sorted_words = sorted(word_counts, key=lambda x: x[1], reverse=True)
    return [word for word, count in sorted_words[:top_n]]

def similarity(a, b):
    return SequenceMatcher(None, a, b).ratio()

def match_keywords(job_keywords, resume_text):
    resume_keywords = extract_keywords(resume_text, top_n=100)
    matched = []
    missing = []

    for job_kw in job_keywords:
        found = False
        for res_kw in resume_keywords:
            if similarity(job_kw, res_kw) > 0.8:
                matched.append(job_kw)
                found = True
                break
        if not found:
            missing.append(job_kw)
    
    return matched, missing

def main():
    print("==== Resume Tailoring Tool ====")
    
    job_description = input("Paste the job description:n")
    resume_text = input("nPaste your resume text:n")

    print("nAnalyzing...n")
    job_keywords = extract_keywords(job_description, top_n=30)
    matched, missing = match_keywords(job_keywords, resume_text)

    print(f"nTop Job Keywords ({len(job_keywords)}):")
    print(", ".join(job_keywords))

    print(f"nMatched Keywords ({len(matched)}):")
    print(", ".join(matched))

    print(f"nMissing Keywords ({len(missing)}):")
    print(", ".join(missing))

    if missing:
        print("nConsider incorporating the missing keywords where appropriate to tailor your resume to the job.")

if __name__ == "__main__":
    main()

Features:

• Keyword extraction using CountVectorizer from scikit-learn.

• Similarity check using difflib for approximate keyword matching.

• Identifies missing job keywords in the resume text.

Requirements:

Install required Python libraries:

bash
CopyEdit
pip install scikit-learn

Enhancements You Can Add:

• Use spacy for smarter NLP-based keyword extraction.

• GUI using tkinter or streamlit.

• Save results to a file or show keyword suggestions with example phrases.

Let me know if you’d like a version with a GUI or tailored for uploading documents.