utils/pdf_processor.py

import pdfplumber

def extract_text_from_pdf(pdf_path: str) -> str:
    """Extract text from PDF file"""
    try:
        with pdfplumber.open(pdf_path) as pdf:
            text = "\n".join([
                page.extract_text() or "" 
                for page in pdf.pages
            ])
        return text.strip()
    except Exception as e:
        print(f"❌ PDF extraction error: {str(e)}")
        return ""

def extract_section(text: str, keywords: list) -> str:
    """
    Extract section from resume based on keywords
    Returns first 1500 chars of section or beginning of text
    
    """
    text_lower = text.lower()
    
    for key in keywords:
        if key in text_lower:
            idx = text_lower.find(key)
            return text[idx:idx+1500]
    
    return text[:1500]