import spacy

from PyPDF2 import PdfReader

import docx

import re

Load the spaCy model for NLP

nlp = spacy.load(‘en_core_web_sm’)

Function to extract text from a PDF file

def extract_text_from_pdf(pdf_path):

reader = PdfReader(pdf_path)

text = ""

for page in reader.pages:

    text += page.extract_text()

return text

Function to extract text from a DOCX file

def extract_text_from_docx(docx_path):

doc = docx.Document(docx_path)

text = ""

for paragraph in doc.paragraphs:

    text += paragraph.text

return text

Function to preprocess text

def preprocess_text(text):

# Lowercase the text

text = text.lower()

# Remove numbers

text = re.sub(r'd+', '', text)

# Remove punctuation

text = re.sub(r'[^ws]', '', text)

return text

Function to extract skills using spaCy’s NER

def extract_skills(text):

skills = []

doc = nlp(text)

for ent in doc.ents:

    if ent.label_ == "SKILL":

        skills.append(ent.text)

return skills

Function to filter resumes based on criteria

def filter_resumes(resume_texts, required_skills):

filtered_resumes = []

for resume_text in resume_texts:

    skills = extract_skills(resume_text)

    if all(skill in skills for skill in required_skills):

        filtered_resumes.append(resume_text)

return filtered_resumes

Example usage

if name == “main“:

# Define the required skills

required_skills = ['python', 'machine learning', 'nlp']



# Extract text from resumes

resume_texts = []

resume_texts.append(preprocess_text(extract_text_from_pdf('resume1.pdf')))

resume_texts.append(preprocess_text(extract_text_from_docx('resume2.docx')))



# Filter resumes

filtered_resumes = filter_resumes(resume_texts, required_skills)



# Print the filtered resumes

for resume in filtered_resumes:

    print("Filtered Resume:n", resume)

Code not running with nlp