Spaces:
Configuration error
Configuration error
File size: 2,739 Bytes
621bdc5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
from flask import Flask, request, render_template
import os
import docx2txt
import PyPDF2
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
app = Flask(__name__)
app.config['UPLOAD_FOLDER'] = 'uploads/'
def extract_text_from_pdf(file_path):
text = ""
with open(file_path, 'rb') as file:
reader = PyPDF2.PdfReader(file)
for page in reader.pages:
text += page.extract_text()
return text
def extract_text_from_docx(file_path):
return docx2txt.process(file_path)
def extract_text_from_txt(file_path):
with open(file_path, 'r', encoding='utf-8') as file:
return file.read()
def extract_text(file_path):
if file_path.endswith('.pdf'):
return extract_text_from_pdf(file_path)
elif file_path.endswith('.docx'):
return extract_text_from_docx(file_path)
elif file_path.endswith('.txt'):
return extract_text_from_txt(file_path)
else:
return ""
@app.route("/")
def matchresume():
return render_template('matchresume.html')
@app.route('/matcher', methods=['POST'])
def matcher():
if request.method == 'POST':
job_description = request.form['job_description']
resume_files = request.files.getlist('resumes')
resumes = []
for resume_file in resume_files:
filename = os.path.join(app.config['UPLOAD_FOLDER'], resume_file.filename)
resume_file.save(filename)
resumes.append(extract_text(filename))
if not resumes or not job_description:
return render_template('matchresume.html', message="Please upload resumes and enter a job description.")
# Vectorize job description and resumes
vectorizer = TfidfVectorizer().fit_transform([job_description] + resumes)
vectors = vectorizer.toarray()
# Calculate cosine similarities
job_vector = vectors[0]
resume_vectors = vectors[1:]
similarities = cosine_similarity([job_vector], resume_vectors)[0]
# Get top 3 resumes and their similarity scores
top_indices = similarities.argsort()[-5:][::-1]
top_resumes = [resume_files[i].filename for i in top_indices]
similarity_scores = [round(similarities[i], 2) for i in top_indices]
return render_template('matchresume.html', message="Top matching resumes:", top_resumes=top_resumes, similarity_scores=similarity_scores)
return render_template('matchresume.html')
if __name__ == '__main__':
if not os.path.exists(app.config['UPLOAD_FOLDER']):
os.makedirs(app.config['UPLOAD_FOLDER'])
app.run(debug=True) |