3d6b44a6e6
- Complete FastAPI backend with SQLite database
- AI-powered resume parsing and job matching using OpenAI
- JWT authentication with role-based access control
- Resume upload, job management, and matching endpoints
- Recruiter dashboard with candidate ranking
- Analytics and skill gap analysis features
- Comprehensive API documentation with OpenAPI
- Alembic database migrations
- File upload support for PDF, DOCX, and TXT resumes
- CORS enabled for frontend integration
🤖 Generated with BackendIM
Co-Authored-By: Claude <noreply@anthropic.com>
58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
import PyPDF2
|
|
import docx
|
|
from typing import Optional
|
|
from pathlib import Path
|
|
|
|
|
|
class ResumeParser:
|
|
@staticmethod
|
|
def extract_text_from_pdf(file_path: str) -> Optional[str]:
|
|
"""Extract text from PDF file"""
|
|
try:
|
|
with open(file_path, 'rb') as file:
|
|
pdf_reader = PyPDF2.PdfReader(file)
|
|
text = ""
|
|
for page in pdf_reader.pages:
|
|
text += page.extract_text() + "\n"
|
|
return text.strip()
|
|
except Exception as e:
|
|
print(f"Error extracting PDF text: {e}")
|
|
return None
|
|
|
|
@staticmethod
|
|
def extract_text_from_docx(file_path: str) -> Optional[str]:
|
|
"""Extract text from DOCX file"""
|
|
try:
|
|
doc = docx.Document(file_path)
|
|
text = ""
|
|
for paragraph in doc.paragraphs:
|
|
text += paragraph.text + "\n"
|
|
return text.strip()
|
|
except Exception as e:
|
|
print(f"Error extracting DOCX text: {e}")
|
|
return None
|
|
|
|
@staticmethod
|
|
def extract_text_from_txt(file_path: str) -> Optional[str]:
|
|
"""Extract text from TXT file"""
|
|
try:
|
|
with open(file_path, 'r', encoding='utf-8') as file:
|
|
return file.read().strip()
|
|
except Exception as e:
|
|
print(f"Error extracting TXT text: {e}")
|
|
return None
|
|
|
|
@classmethod
|
|
def extract_text(cls, file_path: str) -> Optional[str]:
|
|
"""Extract text from file based on extension"""
|
|
file_extension = Path(file_path).suffix.lower()
|
|
|
|
if file_extension == '.pdf':
|
|
return cls.extract_text_from_pdf(file_path)
|
|
elif file_extension == '.docx':
|
|
return cls.extract_text_from_docx(file_path)
|
|
elif file_extension == '.txt':
|
|
return cls.extract_text_from_txt(file_path)
|
|
else:
|
|
print(f"Unsupported file format: {file_extension}")
|
|
return None |