Spaces:
Configuration error
Configuration error
| import os | |
| import re | |
| import PyPDF2 | |
| from docx import Document | |
| from typing import Dict, List | |
| def extract_text_from_pdf(file_path: str) -> str: | |
| """Extract text from PDF file.""" | |
| with open(file_path, 'rb') as file: | |
| reader = PyPDF2.PdfReader(file) | |
| text = "" | |
| for page in reader.pages: | |
| text += page.extract_text() + "\n" | |
| return text | |
| def extract_text_from_docx(file_path: str) -> str: | |
| """Extract text from DOCX file.""" | |
| doc = Document(file_path) | |
| return "\n".join([paragraph.text for paragraph in doc.paragraphs]) | |
| def extract_contact_info(text: str) -> Dict[str, str]: | |
| """Extract contact information from text.""" | |
| # Email pattern | |
| email_pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}' | |
| # Phone pattern (supports various formats) | |
| phone_pattern = r'(\+\d{1,3}[-.\s]?)?\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}' | |
| email = re.search(email_pattern, text) | |
| phone = re.search(phone_pattern, text) | |
| return { | |
| 'email': email.group(0) if email else '', | |
| 'phone': phone.group(0) if phone else '' | |
| } | |
| def extract_skills(text: str) -> List[str]: | |
| """Extract skills by keyword scan (lightweight, no external NLP).""" | |
| skills_list = [ | |
| 'python', 'java', 'javascript', 'c++', 'c#', 'sql', 'html', 'css', | |
| 'machine learning', 'deep learning', 'data science', 'data analysis', | |
| 'project management', 'team leadership', 'agile', 'scrum', 'devops', | |
| 'cloud', 'aws', 'azure', 'gcp', 'docker', 'kubernetes', 'git', 'rest api', | |
| 'graphql', 'mongodb', 'postgresql', 'mysql', 'tensorflow', 'pytorch', | |
| 'pandas', 'numpy', 'spark', 'hadoop', 'nlp' | |
| ] | |
| text_lower = text.lower() | |
| found = set() | |
| for skill in skills_list: | |
| if skill in text_lower: | |
| found.add(skill) | |
| return sorted(found) | |
| def parse_resume(file_path: str) -> Dict: | |
| """Main function to parse resume and extract information.""" | |
| # Determine file type and extract text | |
| file_ext = os.path.splitext(file_path)[1].lower() | |
| if file_ext == '.pdf': | |
| text = extract_text_from_pdf(file_path) | |
| elif file_ext == '.docx': | |
| text = extract_text_from_docx(file_path) | |
| else: | |
| raise ValueError("Unsupported file format. Please upload a PDF or DOCX file.") | |
| # Extract information | |
| contact_info = extract_contact_info(text) | |
| skills = extract_skills(text) | |
| # Extract name (simple approach - first line is often the name) | |
| name = text.split('\n')[0].strip() | |
| return { | |
| 'name': name, | |
| 'email': contact_info['email'], | |
| 'phone': contact_info['phone'], | |
| 'skills': skills, | |
| 'raw_text': text | |
| } | |