Job Description Keyword Extractor

pip install pymupdf nltk wordcloud

import nltk

nltk.download('punkt')

nltk.download('stopwords')

import fitz  # PyMuPDF

import nltk

from nltk.corpus import stopwords

from nltk.tokenize import word_tokenize

from wordcloud import WordCloud

import tkinter as tk

from tkinter import filedialog

import matplotlib.pyplot as plt

import string

def extract_text_from_pdf(pdf_path):

    doc = fitz.open(pdf_path)

    text = ""

    for page in doc:

        text += page.get_text()

    return text

def clean_and_tokenize(text):

    # Lowercase, remove punctuation

    text = text.lower().translate(str.maketrans("", "", string.punctuation))

    tokens = word_tokenize(text)

    # Remove stopwords & short words

    stop_words = set(stopwords.words("english"))

    keywords = [word for word in tokens if word not in stop_words and len(word) > 2]

    return keywords

def generate_wordcloud(keywords):

    word_freq = nltk.FreqDist(keywords)

    wordcloud = WordCloud(width=800, height=400, background_color='white').generate_from_frequencies(word_freq)

    plt.figure(figsize=(10, 5))

    plt.imshow(wordcloud, interpolation="bilinear")

    plt.axis("off")

    plt.title("Top Keywords in Job Description", fontsize=16)

    plt.show()

def main():

    # Open file dialog

    root = tk.Tk()

    root.withdraw()

    file_path = filedialog.askopenfilename(title="Select Job Description PDF", filetypes=[("PDF Files", "*.pdf")])

    if not file_path:

        print("No file selected.")

        return

    print("Processing...")

    text = extract_text_from_pdf(file_path)

    keywords = clean_and_tokenize(text)

    generate_wordcloud(keywords)

    print("\nTop 20 Keywords:")

    for word, freq in nltk.FreqDist(keywords).most_common(20):

        print(f"{word} - {freq}")

if __name__ == "__main__":

    main()