Spaces:
Paused
Paused
| import re | |
| from pathlib import Path | |
| from pdfminer.high_level import extract_text as pdf_extract_text | |
| from docx import Document | |
| class ResumeParser: | |
| def __init__(self): | |
| pass | |
| def extract_text(self, file_path: str) -> str: | |
| """Extract text from PDF or DOCX files""" | |
| path = Path(file_path) | |
| if path.suffix.lower() == ".pdf": | |
| text = pdf_extract_text(file_path) | |
| return re.sub(r'\s+', ' ', text).strip() | |
| elif path.suffix.lower() == ".docx": | |
| doc = Document(file_path) | |
| return "\n".join([p.text for p in doc.paragraphs if p.text.strip()]) | |
| else: | |
| raise ValueError("Unsupported file format") | |
| def extract_name(self, text: str) -> str: | |
| """Extract name from resume text""" | |
| # Try to find name at the beginning of document | |
| first_lines = [line.strip() for line in text.split('\n')[:10] if line.strip()] | |
| for line in first_lines: | |
| # Simple name pattern (2-4 words, all starting with capital) | |
| if re.match(r'^[A-Z][a-z]+(?:\s+[A-Z][a-z]+){1,3}$', line): | |
| if not any(word.lower() in ['resume', 'cv', 'curriculum'] for word in line.split()): | |
| return line | |
| # Fallback: return first non-empty line that looks like a name | |
| for line in first_lines: | |
| if 2 <= len(line.split()) <= 4 and line[0].isupper(): | |
| return line | |
| return "Not Found" | |
| def extract_sections(self, text: str) -> dict: | |
| """Extract skills, education, and experience using regex""" | |
| results = { | |
| "skills": [], | |
| "education": [], | |
| "experience": [] | |
| } | |
| # Extract skills | |
| skills_match = re.search( | |
| r'(?:skills|technologies|expertise)[:\s]*(.*?)(?:\n\n|\n\s*\n|$)', | |
| text, re.IGNORECASE | |
| ) | |
| if skills_match: | |
| skills_text = skills_match.group(1) | |
| results["skills"] = [s.strip() for s in re.split(r'[,;]', skills_text) if s.strip()] | |
| # Extract education | |
| edu_match = re.search( | |
| r'(?:education|degrees?)[:\s]*(.*?)(?:\n\n|\n\s*\n|$)', | |
| text, re.IGNORECASE | |
| ) | |
| if edu_match: | |
| results["education"] = [e.strip() for e in edu_match.group(1).split('\n') if e.strip()] | |
| # Extract experience | |
| exp_match = re.search( | |
| r'(?:experience|work history|employment)[:\s]*(.*?)(?:\n\n|\n\s*\n|$)', | |
| text, re.IGNORECASE | |
| ) | |
| if exp_match: | |
| results["experience"] = [x.strip() for x in exp_match.group(1).split('\n') if x.strip()] | |
| return results | |
| def parse_resume(self, file_path: str) -> dict: | |
| """Main parsing function""" | |
| try: | |
| text = self.extract_text(file_path) | |
| if not text or len(text.strip()) < 10: | |
| return { | |
| "name": "Error: Empty file", | |
| "skills": [], | |
| "education": [], | |
| "experience": [] | |
| } | |
| name = self.extract_name(text) | |
| sections = self.extract_sections(text) | |
| return { | |
| "name": name, | |
| "skills": sections["skills"][:10], # Limit to 10 skills | |
| "education": sections["education"][:3], # Limit to 3 items | |
| "experience": sections["experience"][:3] # Limit to 3 items | |
| } | |
| except Exception as e: | |
| return { | |
| "name": f"Error: {str(e)}", | |
| "skills": [], | |
| "education": [], | |
| "experience": [] | |
| } | |
| # Global instance | |
| resume_parser = ResumeParser() | |
| def parse_resume(file_path: str) -> dict: | |
| """Public interface for resume parsing""" | |
| return resume_parser.parse_resume(file_path) |